REVIEW 3 major objections 4 minor 300 references
Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution
T0 review · 3 major / 4 minor · reviewed 2026-08-01 · deepseek-v4-flash
Pith's one-line read Routing by restoration difficulty—hard images to a detail-preserving 4×-VAE diffusion expert, easy ones to a fast 8×-VAE expert—yields better perceptual quality at lower compute than one-size-fits-all diffusion super-resolution.
desk verdict The routing idea is real and the easy/hard analysis is nice, but as written the inference-time router needs the ground-truth image, so the central claim doesn't hold until a learned difficulty predictor is added. read the letter →
The pith
A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.
The reading
What carries the argument
The load-bearing mechanism is the difficulty-aware router. It computes, via the 2D Fourier transform and a high-frequency mask, the score d = 1 − E_high(I_deg)/E_high(I_gt), which falls in [0,1] and measures how much high-frequency spectral energy the degradation has removed. That score is compared to a user-settable threshold τ (default: the training set's median difficulty) to send the input to either Expert-D4, which uses a 4×-downsampling VAE and is LoRA-tuned on 80% hard plus 20% easy samples, or Expert-D8, which uses the standard 8×-downsampling VAE and is LoRA-tuned on the complementary mix. Both experts share the same diffusion UNet and one-step denoising, so the routing decision is
What would settle it
Compute d for all test images using Eq. (2) with ground truth, then train a neural network that takes only I_deg as input and tries to predict d. If the predicted routing (using that proxy's scores) yields quality or efficiency no better than always sending every image to Expert-D4 (or always to Expert-D8), the central claim that difficulty-aware routing helps would be refuted. A second, simpler check: inspect whether the authors' reported benchmark numbers were produced using the ground-truth-based oracle d, since if they were, the same numbers would not be reproducible at deployment time whe
Extended reading notes
Core claim
The paper's core discovery is that a pair of expert diffusion networks differing only in their VAE's spatial compression ratio—4× versus 8×—can be trained with an 80/20 mixed-sampling strategy to produce complementary strengths, and a simple threshold on the high-frequency energy attenuation score can then assign each input to the right expert. On DIV2K-val, RealSR, and DRealSR, the routed system ('DDR-SR-1') reports the best SSIM, LPIPS, and CLIPIQA among compared one-step and multi-step diffusion methods, and the 4× expert alone runs at 1.81T FLOPs versus 2.27T for the strongest one-step baseline. The author's claim is that the rigid 8× VAE compression in standard latent diffusion irrevers
Load-bearing premise
The difficulty score d is computed from both the degraded image and its ground-truth high-resolution counterpart; in real-world deployment the ground truth does not exist, and the paper does not describe a learned network that estimates d from the degraded image alone, so the automatic routing cannot be executed as specified without oracle access.
Editorial extensions
If this is right
- Diffusion super-resolution no longer needs a single fixed VAE compression ratio; capacity can be matched to input difficulty, improving perceptual fidelity on hard samples.
- Since easy inputs dominate many real-world collections, average computational cost per image can drop below what a single high-capacity model would need.
- The mixed-training recipe (80/20 in opposing directions) keeps each expert robust to routing mistakes without sacrificing specialization.
- The user-adjustable threshold turns the quality/efficiency trade-off into a deployable knob, so practitioners can select a point on the curve at runtime.
- The routing logic is model-agnostic in principle and could attach to any latent-diffusion restoration system whose VAE compression ratio can be varied.
Reading between the lines
- The difficulty estimator as defined requires the ground-truth HR image; to make DDR-SR deployable, the authors would need to train a proxy network that predicts d from the degraded image alone, and the reported gains would then depend on how well that proxy recovers the oracle ranking.
- The global Fourier energy score may be a coarse difficulty signal: an image with a small, heavily degraded text region could receive a low difficulty score if most of its energy is elsewhere; a spatially localized or region-weighted difficulty predictor might improve routing accuracy.
- The 4×/8× choice is a two-point discretization of a continuous capacity spectrum; interpolating the VAE compression ratio between 4 and 8, or routing among more than two experts, might smooth the quality cliff at the threshold and yield a finer trade-off.
- Because the two experts share the UNet, the router could in principle be folded into a single model that selects the VAE at inference time, reducing duplication of the diffusion backbone.
Signed reviews
Editorial analysis
A structured set of objections, weighed in public.
Referee Report
Summary. The paper proposes DDR-SR, a difficulty-aware dynamic routing framework for diffusion-based real-world image super-resolution. It defines a difficulty score based on high-frequency spectral energy attenuation between the degraded image and its ground-truth counterpart, splits training data into easy and hard subsets, and trains two LoRA-adapted expert networks: Expert-D4 with a 4x-compression VAE and Expert-D8 with an 8x-compression VAE. At inference, inputs are routed to one of the two experts according to a threshold on the difficulty score. The method is evaluated on DIV2K-val, RealSR, and DRealSR against several multi-step and one-step diffusion baselines, and the paper claims superior quality and a tunable quality/efficiency trade-off.
Significance. If the method worked as described, the idea of adaptively choosing VAE compression according to per-image difficulty would be useful for the Real-ISR community: it is a plausible way to preserve fine details for hard inputs while saving computation on easy ones. The paper also provides real benchmark numbers and a reasonable experimental setup. However, as written, the central mechanism is not implementable because the routing decision requires the ground-truth image, the efficiency claim is based on an incomplete comparison, and no ablation isolates the effect of routing. None of these issues is merely cosmetic: each concerns the core contribution of the paper.
major comments (3)
- [Section 3.2 and Algorithm 2] The routing difficulty score defined in Eq. (2), d = 1 - E_high(I_deg)/E_high(I_gt), requires the ground-truth image I_gt. Algorithm 2 explicitly writes 'd <- E_diff(I_deg, I_gt)'. In real-world deployment I_gt does not exist, yet the paper nowhere specifies, trains, or evaluates a learned estimator that maps only I_deg to d. Without such a proxy, the automatic dynamic routing at inference cannot be executed, and the Table 1 results must have been obtained either with oracle access to ground truth (which would inflate reported gains) or with an undocumented approximation. Since dynamic routing is the paper's stated core contribution, this is a load-bearing flaw. The authors need to provide a fully specified deployable difficulty estimator and re-run the benchmark evaluation without using I_gt at inference.
- [Section 4.2, Table 2] The efficiency comparison reports only Expert-D4 (1.81T FLOPs, 1.63B parameters) and omits the full DDR-SR system. The actual inference pipeline also includes the difficulty estimator/router and, under the default median split, routes roughly half the inputs to Expert-D8 and half to Expert-D4. The paper never reports the expected or measured FLOPs/latency of the complete DDR-SR model, nor the router's additional cost. Consequently, the Conclusion's claim of 'a tunable trade-off between quality and speed' is not supported by the efficiency data presented. The authors should report full DDR-SR complexity, including router overhead, for at least a few routing ratios.
- [Section 4.3] The ablation study is limited to LoRA rank configurations for Expert-D4 and Expert-D8 (Tables 3 and 4). It does not compare DDR-SR against Expert-D4-only or Expert-D8-only, nor does it vary the routing threshold tau. Without these comparisons, the reported improvement cannot be attributed to dynamic routing; it could come from the higher-capacity Expert-D4 architecture or from the mixed training strategy. The paper needs ablations that isolate the routing decision, e.g., D4-only, D8-only, DDR-SR at tau=median, and DDR-SR at other routing ratios, with matched training budgets.
minor comments (4)
- [Section 4.2] Text says 'DiffBIR, SeeSR, PASD, and DiffBIR exhibit better performance' — DiffBIR is listed twice; the intended set is unclear.
- [Figure 4 / Section 4.2] In the qualitative discussion, 'DRR-SR' is a typo for 'DDR-SR'.
- [Section 4.2 / Table 2] The text says Expert-D4 has '1.65B parameters', but Table 2 lists 1.63B. Please reconcile.
- [Eq. (3)] The formula for z_SR is typeset ambiguously; it should be z_SR = (z - sqrt(1 - alpha_bar_t) * eps_8(z, c_t, t)) / sqrt(alpha_bar_t) or written as an explicit one-step denoising expression.
Circularity Check
Routing score is computed from ground truth in Eq. (2)/Algorithm 2, making benchmark routing oracle-based rather than predicted.
-
self definitional
[Eq. (2), Section 3.2; Algorithm 2 line 2; Section 3.4]
"The restoration difficulty of a degraded image is defined as: d = 1 − E_high(I_deg)/E_high(I_gt) ... [Algorithm 2] Compute difficulty score: d ← E_diff(I_deg, I_gt)"
The routing signal d is defined as a normalized comparison against the ground-truth HR image. Algorithm 2 calls this estimator with I_gt at inference: d ← E_diff(I_deg, I_gt). No learned proxy mapping only I_deg to d is introduced or trained anywhere in the paper. Therefore the route choices and benchmark numbers for DDR-SR-1 are not predictions from the degraded input; they are constructed from the target image. The claimed 'automatic assignment' and 'difficulty-aware dynamic routing' thus reduce by construction to oracle access to the label, and the advertised quality/speed trade-off is not demonstrated for deployment.
full rationale
The central derivational flaw is that the difficulty score used to make the routing decision is defined in terms of the ground-truth image (Eq. 2) and is explicitly evaluated with I_gt in Algorithm 2 at inference time. The paper never describes or trains a network that predicts d from the degraded image alone, so the reported DDR-SR-1 results in Table 1 depend on oracle routing rather than an executable sample-adaptive mechanism. This makes the core 'dynamic routing' claim partly circular: the decision variable is not predicted from the input but read off from the target. The other components—two VAE-modulated experts, LoRA tuning, mixed training, and the loss combination—are independent and not circularly justified, and there is no load-bearing self-citation or imported uniqueness theorem. However, because the central contribution is evaluated by a route selector that uses ground truth, the overall circularity score is elevated.
Assumptions & free parameters
free parameters (5)
- Loss weights λ1, λ2 =
λ1=2, λ2=1
- Mixing ratios α, β =
α=0.8, β=0.2
- Routing threshold τ =
median of training difficulties
- LoRA ranks =
VAE-D4 4, UNet-D4 4; VAE-D8 16, UNet-D8 4
- High-frequency mask threshold M_high =
not specified (radial threshold)
assumptions (4)
- domain assumption Real-world degradations act predominantly as low-pass filters, so high-frequency energy attenuation (Eq. 2) measures restoration difficulty.
- domain assumption A 4×-compression VAE preserves fine details and is compatible with the pretrained SD 2.1 UNet.
- ad hoc to paper Ground truth is available when computing the routing score.
- domain assumption Stable diffusion priors and VAE-D8 from SD 2.1 retain enough prior for one-step SR after LoRA tuning.
invented entities (2)
-
Difficulty score d (high-frequency energy attenuation)
-
Expert-D4 / Expert-D8 router
Cite this review
Pith. "Pith review of Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution." pith.science (2026). https://pith.science/paper/Y5BKEGMF
@misc{pith2026260715711,
author = {Pith},
title = {Pith review of: Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution},
year = {2026},
howpublished = {\url{https://pith.science/paper/Y5BKEGMF}},
note = {Machine review of arXiv:2607.15711}
}
read the original abstract
Diffusion-based methods have achieved impressive performance in real-world image super-resolution (Real-ISR) by leveraging large pre-trained stable diffusion (SD) models as powerful generative priors. However, these methods still face two key limitations. First, existing SD-based one-step and multi-step Real-ISR approaches adopt a unified processing paradigm for all input samples, ignoring the varying restoration difficulty across images. Second, the aggressive resolution reduction of the VAE in SD models (e.g., 8x downsampling) leads to irreversible loss of fine-scale details, which cannot be recovered by the subsequent diffusion process. To address these limitations, we propose a Difficulty-aware Dynamic Routing (DDR) strategy that overcomes the rigid, one-size-fits-all processing paradigm. Specifically, we first design a difficulty estimator to predict the restoration cost of each input image, enabling automatic assignment to a network of appropriate capacity. Then, we construct a set of Real-ISR networks with varying model capacities by modulating the spatial downsampling ratio of the VAE in the SD backbone, thereby preserving more high-frequency information for challenging cases while maintaining efficiency for simpler inputs. Extensive experiments have demonstrated the superior efficiency and effectiveness of the proposed model compared to recent state-of-the-art methods.
Figures
Figures from the paper (2 more)
Reference graph
Works this paper leans on
-
[1]
Proceedings of the IEEE/CVF international conference on computer vision , pages=
Toward real-world single image super-resolution: A new benchmark and a new model , author=. Proceedings of the IEEE/CVF international conference on computer vision , pages=
-
[2]
European conference on computer vision , pages=
Component divide-and-conquer for real-world image super-resolution , author=. European conference on computer vision , pages=
-
[3]
Image super-resolution based on dictionary learning and anchored neighborhood regression with mutual incoherence , author=. Proc
-
[4]
ECCV , year=
Accelerating the super-resolution convolutional neural network , author=. ECCV , year=
-
[5]
TPAMI , year=
Image super-resolution using deep convolutional networks , author=. TPAMI , year=
-
[6]
CVPR , year=
Accurate image super-resolution using very deep convolutional networks , author=. CVPR , year=
-
[7]
ICCV , year=
Dual Aggregation Transformer for Image Super-Resolution , author=. ICCV , year=
-
[8]
TPAMI , year=
Deep learning for image super-resolution: A survey , author=. TPAMI , year=
Show all 300 references
-
[9]
ICCV , year=
Dslr-quality photos on mobile devices with deep convolutional networks , author=. ICCV , year=
-
[10]
ICCV , year=
Real-ESRGAN: Training real-world blind super-resolution with pure synthetic data , author=. ICCV , year=
-
[11]
CVPRW , year=
Real-world super-resolution via kernel estimation and noise injection , author=. CVPRW , year=
-
[12]
ECCV , year=
Component divide-and-conquer for real-world image super-resolution , author=. ECCV , year=
-
[13]
CVPR , year=
Robustifying token attention for vision transformers , author=. CVPR , year=
-
[14]
NeurIPS , year=
Denoising diffusion probabilistic models , author=. NeurIPS , year=
-
[15]
ICLR , year=
Score-based generative modeling through stochastic differential equations , author=. ICLR , year=
-
[16]
CVPR , year=
Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn , title=. CVPR , year=
-
[17]
2023 , howpublished=
Black Forest Labs , title=. 2023 , howpublished=
2023
-
[18]
ICCV , year=
Adding Conditional Control to Text-to-Image Diffusion Models , author=. ICCV , year=
-
[19]
arXiv preprint arXiv:2307.01952 , year=
Sdxl: Improving latent diffusion models for high-resolution image synthesis , author=. arXiv preprint arXiv:2307.01952 , year=
-
[20]
ECCV , year=
Adversarial diffusion distillation , author=. ECCV , year=
-
[21]
CVPR , year=
Ufogen: You forward once large scale text-to-image generation via diffusion gans , author=. CVPR , year=
-
[22]
arXiv preprint arXiv:2403.12015 , year=
Fast high-resolution image synthesis with latent adversarial diffusion distillation , author=. arXiv preprint arXiv:2403.12015 , year=
-
[23]
ICLR , year=
Diffusion-gan: Training gans with diffusion , author=. ICLR , year=
-
[24]
CVPR , year=
Swiftbrush: One-step text-to-image diffusion model with variational score distillation , author=. CVPR , year=
-
[25]
NeurIPS , year=
Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation , author=. NeurIPS , year=
-
[26]
ICLR , year=
Denoising diffusion implicit models , author=. ICLR , year=
-
[27]
NeurIPS , year=
Elucidating the design space of diffusion-based generative models , author=. NeurIPS , year=
-
[28]
ICLR , year=
Pseudo numerical methods for diffusion models on manifolds , author=. ICLR , year=
-
[29]
NeurIPS , year=
Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps , author=. NeurIPS , year=
-
[30]
arXiv preprint arXiv:2211.01095 , year=
Dpm-solver++: Fast solver for guided sampling of diffusion probabilistic models , author=. arXiv preprint arXiv:2211.01095 , year=
-
[31]
NeurIPS , year=
Unipc: A unified predictor-corrector framework for fast sampling of diffusion models , author=. NeurIPS , year=
-
[32]
arXiv preprint arXiv:2303.04248 , year=
Tract: Denoising diffusion models with transitive closure time-distillation , author=. arXiv preprint arXiv:2303.04248 , year=
-
[33]
CVPR , year=
High-resolution image synthesis with latent diffusion models , author=. CVPR , year=
-
[34]
Forty-first International Conference on Machine Learning , year=
Scaling rectified flow transformers for high-resolution image synthesis , author=. Forty-first International Conference on Machine Learning , year=
-
[35]
arXiv preprint arXiv:2209.03003 , year=
Flow straight and fast: Learning to generate and transfer data with rectified flow , author=. arXiv preprint arXiv:2209.03003 , year=
-
[36]
CVPR , year=
On distillation of guided diffusion models , author=. CVPR , year=
-
[37]
ICLR , year=
Progressive distillation for fast sampling of diffusion models , author=. ICLR , year=
-
[38]
ICML , year=
Consistency models , author=. ICML , year=
-
[39]
ICML , year=
Fast sampling of diffusion models via operator learning , author=. ICML , year=
-
[40]
CVPR , year=
One-step diffusion with distribution matching distillation , author=. CVPR , year=
-
[41]
ICLR , year=
Instaflow: One step is enough for high-quality diffusion-based text-to-image generation , author=. ICLR , year=
-
[42]
NeurIPS , year=
One-step diffusion distillation via deep equilibrium models , author=. NeurIPS , year=
-
[43]
arXiv preprint arXiv:2405.14867 , year=
Improved Distribution Matching Distillation for Fast Image Synthesis , author=. arXiv preprint arXiv:2405.14867 , year=
-
[44]
arXiv preprint arXiv:2405.07510 , year=
Perflow: Piecewise rectified flow as universal plug-and-play accelerator , author=. arXiv preprint arXiv:2405.07510 , year=
-
[45]
ICCV , year=
Real-esrgan: Training real-world blind super-resolution with pure synthetic data , author=. ICCV , year=
-
[46]
COMMUN ACM , year=
Generative adversarial networks , author=. COMMUN ACM , year=
-
[47]
NeurIPS , year=
Visual autoregressive modeling: Scalable image generation via next-scale prediction , author=. NeurIPS , year=
-
[48]
CVPR , year=
Seesr: Towards semantics-aware real-world image super-resolution , author=. CVPR , year=
-
[49]
ECCV , year=
Pixel-aware stable diffusion for realistic image super-resolution and personalized stylization , author=. ECCV , year=
-
[50]
ECCV , year=
Diffbir: Towards blind image restoration with generative diffusion prior , author=. ECCV , year=
-
[51]
CVPR , year=
Scaling up to excellence: Practicing model scaling for photo-realistic image restoration in the wild , author=. CVPR , year=
-
[52]
CVPR , year=
SinSR: Diffusion-based image super-resolution in a single step , author=. CVPR , year=
-
[53]
arXiv preprint arXiv:2406.08177 , year=
One-Step Effective Diffusion Network for Real-World Image Super-Resolution , author=. arXiv preprint arXiv:2406.08177 , year=
-
[54]
arXiv preprint arXiv:2410.04224 , year=
Distillation-free one-step diffusion for real-world image super-resolution , author=. arXiv preprint arXiv:2410.04224 , year=
-
[55]
arXiv preprint arXiv:2408.07476 , year=
One step diffusion-based super-resolution with time-aware distillation , author=. arXiv preprint arXiv:2408.07476 , year=
-
[56]
arXiv preprint arXiv:2411.18263 , year=
TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution , author=. arXiv preprint arXiv:2411.18263 , year=
-
[57]
IJCV , year=
Exploiting diffusion prior for real-world image super-resolution , author=. IJCV , year=
-
[58]
NeurIPS , year=
Resshift: Efficient diffusion model for image super-resolution by residual shifting , author=. NeurIPS , year=
-
[59]
CVPR , year=
The unreasonable effectiveness of deep features as a perceptual metric , author=. CVPR , year=
-
[60]
2019 , eprint=
Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model , author=. 2019 , eprint=
2019
-
[61]
TPAMI , year=
Image quality assessment: Unifying structure and texture similarity , author=. TPAMI , year=
-
[62]
TIP , year=
A feature-enriched completely blind image quality evaluator , author=. TIP , year=
-
[63]
ICCV , year=
Musiq: Multi-scale image quality transformer , author=. ICCV , year=
-
[64]
CVPR , year=
Maniqa: Multi-dimension attention network for no-reference image quality assessment , author=. CVPR , year=
-
[65]
AAAI , year=
Exploring clip for assessing the look and feel of images , author=. AAAI , year=
-
[66]
CVPR , year=
A Style-Based Generator Architecture for Generative Adversarial Networks , author=. CVPR , year=
-
[67]
CVPRW , year=
Lsdir: A large scale dataset for image restoration , author=. CVPRW , year=
-
[68]
CVPRW , year=
Ntire 2017 challenge on single image super-resolution: Dataset and study , author=. CVPRW , year=
2017
-
[69]
IEEE TIP , year=
Topiq: A top-down approach from semantics to distortions for image quality assessment , author=. IEEE TIP , year=
-
[70]
arXiv preprint arXiv:2312.17090 , year=
Q-align: Teaching lmms for visual scoring via discrete text-defined levels , author=. arXiv preprint arXiv:2312.17090 , year=
-
[71]
arXiv preprint arXiv:2010.14701 , year=
Scaling laws for autoregressive generative modeling , author=. arXiv preprint arXiv:2010.14701 , year=
2010 arXiv
-
[72]
arXiv preprint arXiv:2106.09685 , year=
Lora: Low-rank adaptation of large language models , author=. arXiv preprint arXiv:2106.09685 , year=
-
[73]
International Conference on Computer Vision (ICCV) , year=
StableSR: Boosting Real-World Image Super-Resolution via Time-Aware Diffusion , author=. International Conference on Computer Vision (ICCV) , year=
-
[74]
, author=
Lora: Low-rank adaptation of large language models. , author=. ICLR , volume=
-
[75]
Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
Fine-structure preserved real-world image super-resolution via transfer vae training , author=. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
-
[76]
Proceedings of the 30th ACM International Conference on Multimedia , pages=
Real-world blind super-resolution via feature matching with implicit high-resolution priors , author=. Proceedings of the 30th ACM International Conference on Multimedia , pages=
-
[77]
arXiv preprint arXiv:2307.12348 , year=
Resshift: Efficient diffusion model for image super-resolution by residual shifting , author=. arXiv preprint arXiv:2307.12348 , year=
-
[78]
Journal of Machine Learning Research , volume=
Visualizing Data using t-SNE , author=. Journal of Machine Learning Research , volume=
-
[79]
arXiv preprint arXiv:2503.11073 , year=
Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models , author=. arXiv preprint arXiv:2503.11073 , year=
-
[80]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Classsr: A general framework to accelerate super-resolution networks by data characteristic , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[81]
arXiv preprint arXiv:2406.07255 , year=
Towards realistic data generation for real-world super-resolution , author=. arXiv preprint arXiv:2406.07255 , year=
-
[82]
arXiv preprint arXiv:2503.20287 , year=
InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction , author=. arXiv preprint arXiv:2503.20287 , year=
-
[83]
arXiv preprint arXiv:2506.01430 , year=
DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing , author=. arXiv preprint arXiv:2506.01430 , year=
-
[84]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
NTIRE 2024 restore any image model (RAIM) in the wild challenge , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
2024
-
[85]
arXiv preprint arXiv:2501.06838 , year=
Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution , author=. arXiv preprint arXiv:2501.06838 , year=
-
[86]
arXiv preprint arXiv:2411.10798 , year=
Unveiling hidden details: A raw data-enhanced paradigm for real-world super-resolution , author=. arXiv preprint arXiv:2411.10798 , year=
-
[87]
Proceedings of the Computer Vision and Pattern Recognition Conference , pages=
The power of context: How multimodality improves image super-resolution , author=. Proceedings of the Computer Vision and Pattern Recognition Conference , pages=
-
[88]
arXiv preprint arXiv:2405.07023 , year=
Efficient real-world image super-resolution via adaptive directional gradient convolution , author=. arXiv preprint arXiv:2405.07023 , year=
-
[89]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Reflash dropout in image super-resolution , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[90]
Information Fusion , volume=
Real-world single image super-resolution: A brief review , author=. Information Fusion , volume=. 2022 , publisher=
2022
-
[91]
TPAMI , volume=
Blind image super-resolution: A survey and beyond , author=. TPAMI , volume=. 2022 , publisher=
2022
-
[92]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Blind super-resolution with iterative kernel correction , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[93]
Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part IV 13 , pages=
Learning a deep convolutional network for image super-resolution , author=. Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part IV 13 , pages=. 2014 , organization=
2014
-
[94]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
A model-driven deep neural network for single image rain removal , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[95]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Progressive image deraining networks: A better and simpler baseline , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[96]
Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14 , pages=
Single image dehazing via multi-scale convolutional neural networks , author=. Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14 , pages=. 2016 , organization=
2016
-
[97]
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
Image deblurring via extreme channels prior , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
-
[98]
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
Scale-recurrent network for deep image deblurring , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
-
[99]
Proceedings of the European conference on computer vision (ECCV) , pages=
Multi-scale residual network for image super-resolution , author=. Proceedings of the European conference on computer vision (ECCV) , pages=
-
[100]
Proceedings of the 29th ACM international conference on multimedia , pages=
Feedback network for mutually boosted stereo image super-resolution and disparity estimation , author=. Proceedings of the 29th ACM international conference on multimedia , pages=
-
[101]
Proceedings of the IEEE/CVF international conference on computer vision , pages=
Swinir: Image restoration using swin transformer , author=. Proceedings of the IEEE/CVF international conference on computer vision , pages=
-
[102]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Pre-trained image processing transformer , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[103]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Activating more pixels in image super-resolution transformer , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[104]
European Conference on Computer Vision , pages=
Efficient long-range attention network for image super-resolution , author=. European Conference on Computer Vision , pages=. 2022 , organization=
2022
-
[105]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Restormer: Efficient transformer for high-resolution image restoration , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[106]
IEEE Transactions on Multimedia , volume=
Efficient and accurate multi-scale topological network for single image dehazing , author=. IEEE Transactions on Multimedia , volume=. 2021 , publisher=
2021
-
[107]
Communications of the ACM , volume=
Generative adversarial networks , author=. Communications of the ACM , volume=. 2020 , publisher=
2020
-
[108]
Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
Designing a practical degradation model for deep blind image super-resolution , author=. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
-
[109]
Proceedings of the AAAI Conference on Artificial Intelligence , volume=
T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models , author=. Proceedings of the AAAI Conference on Artificial Intelligence , volume=
-
[110]
European Conference on Computer Vision , pages=
Xpsr: Cross-modal priors for diffusion-based image super-resolution , author=. European Conference on Computer Vision , pages=. 2024 , organization=
2024
-
[111]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[112]
arXiv preprint arXiv:2410.18666 , year=
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation , author=. arXiv preprint arXiv:2410.18666 , year=
-
[113]
arXiv preprint arXiv:2412.03017 , year=
Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach , author=. arXiv preprint arXiv:2412.03017 , year=
-
[114]
IEEE transactions on image processing , volume=
Image quality assessment: from error visibility to structural similarity , author=. IEEE transactions on image processing , volume=. 2004 , publisher=
2004
-
[115]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Details or artifacts: A locally discriminative learning approach to realistic image super-resolution , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[116]
European Conference on Computer Vision , pages=
Efficient and degradation-adaptive network for real-world image super-resolution , author=. European Conference on Computer Vision , pages=. 2022 , organization=
2022
-
[117]
2023 , booktitle=
DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models , author=. 2023 , booktitle=
2023
-
[118]
Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
A benchmark for chinese-english scene text image super-resolution , author=. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
-
[119]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Generative Diffusion Prior for Unified Image Restoration and Enhancement , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[120]
Special lecture on IE , volume=
Variational autoencoder based anomaly detection using reconstruction probability , author=. Special lecture on IE , volume=
-
[121]
arXiv preprint arXiv:2306.06513 , year=
Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration , author=. arXiv preprint arXiv:2306.06513 , year=
-
[122]
Advances in Neural Information Processing Systems , volume=
Photorealistic text-to-image diffusion models with deep language understanding , author=. Advances in Neural Information Processing Systems , volume=
-
[123]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Recognize anything: A strong image tagging model , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[124]
Advances in Neural Information Processing Systems , volume=
Denoising diffusion restoration models , author=. Advances in Neural Information Processing Systems , volume=
-
[125]
arXiv preprint arXiv:2212.00490 , year=
Zero-shot image restoration using denoising diffusion null-space model , author=. arXiv preprint arXiv:2212.00490 , year=
-
[126]
arXiv preprint arXiv:2305.07015 , year=
Exploiting Diffusion Prior for Real-World Image Super-Resolution , author=. arXiv preprint arXiv:2305.07015 , year=
-
[127]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Adapt or perish: Adaptive sparse transformer with attentive feature refinement for image restoration , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[128]
Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
Mb-taylorformer: Multi-branch efficient transformer expanded by taylor formula for image dehazing , author=. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
-
[129]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Image dehazing transformer with transmission-aware 3d position embedding , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[130]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Contrastive learning for compact single image dehazing , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[131]
Advances in Neural Information Processing Systems , volume=
PGDiff: Guiding diffusion models for versatile face restoration via partial guidance , author=. Advances in Neural Information Processing Systems , volume=
-
[132]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Gan prior embedded network for blind face restoration in the wild , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[133]
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
Deep residual learning for image recognition , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
-
[134]
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
You only look once: Unified, real-time object detection , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
-
[135]
International Conference on Machine Learning , pages=
Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation , author=. International Conference on Machine Learning , pages=. 2022 , organization=
2022
-
[136]
arXiv preprint arXiv:2208.01626 , year=
Prompt-to-prompt image editing with cross attention control , author=. arXiv preprint arXiv:2208.01626 , year=
-
[137]
arXiv preprint arXiv:2305.15347 , year=
A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence , author=. arXiv preprint arXiv:2305.15347 , year=
-
[138]
Physical Review E , volume=
Equilibrium free-energy differences from nonequilibrium measurements: A master-equation approach , author=. Physical Review E , volume=. 1997 , publisher=
1997
-
[139]
Statistics and computing , volume=
Annealed importance sampling , author=. Statistics and computing , volume=. 2001 , publisher=
2001
-
[140]
International conference on machine learning , pages=
Deep unsupervised learning using nonequilibrium thermodynamics , author=. International conference on machine learning , pages=. 2015 , organization=
2015
-
[141]
arXiv preprint arXiv:2306.03514 , year=
Recognize Anything: A Strong Image Tagging Model , author=. arXiv preprint arXiv:2306.03514 , year=
-
[142]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
A style-based generator architecture for generative adversarial networks , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[143]
Proceedings of the IEEE conference on computer vision and pattern recognition workshops , pages=
Ntire 2017 challenge on single image super-resolution: Dataset and study , author=. Proceedings of the IEEE conference on computer vision and pattern recognition workshops , pages=
2017
-
[144]
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) , pages=
Div8k: Diverse 8k resolution image dataset , author=. 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) , pages=. 2019 , organization=
2019
-
[145]
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
Recovering realistic texture in image super-resolution by deep spatial feature transform , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
-
[146]
Proceedings of the IEEE conference on computer vision and pattern recognition workshops , pages=
Ntire 2017 challenge on single image super-resolution: Methods and results , author=. Proceedings of the IEEE conference on computer vision and pattern recognition workshops , pages=
2017
-
[147]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Investigating tradeoffs in real-world video super-resolution , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[148]
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
The unreasonable effectiveness of deep features as a perceptual metric , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
-
[149]
IEEE transactions on pattern analysis and machine intelligence , volume=
Image quality assessment: Unifying structure and texture similarity , author=. IEEE transactions on pattern analysis and machine intelligence , volume=. 2020 , publisher=
2020
-
[150]
Advances in neural information processing systems , volume=
Gans trained by a two time-scale update rule converge to a local nash equilibrium , author=. Advances in neural information processing systems , volume=
-
[151]
Proceedings of the AAAI Conference on Artificial Intelligence , volume=
Exploring clip for assessing the look and feel of images , author=. Proceedings of the AAAI Conference on Artificial Intelligence , volume=
-
[152]
Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
Musiq: Multi-scale image quality transformer , author=. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
-
[153]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Maniqa: Multi-dimension attention network for no-reference image quality assessment , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[154]
IEEE Transactions on Image Processing , volume=
A feature-enriched completely blind image quality evaluator , author=. IEEE Transactions on Image Processing , volume=. 2015 , publisher=
2015
-
[155]
arXiv preprint arXiv:1412.6980 , year=
Adam: A method for stochastic optimization , author=. arXiv preprint arXiv:1412.6980 , year=
-
[156]
International Conference on Machine Learning , pages=
Improved denoising diffusion probabilistic models , author=. International Conference on Machine Learning , pages=. 2021 , organization=
2021
-
[157]
arXiv preprint arXiv:1912.02781 , year=
Augmix: A simple data processing method to improve robustness and uncertainty , author=. arXiv preprint arXiv:1912.02781 , year=
1912 arXiv
-
[158]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Taming transformers for high-resolution image synthesis , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[159]
arXiv preprint arXiv:2308.06721 , year=
Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models , author=. arXiv preprint arXiv:2308.06721 , year=
-
[160]
Advances in neural information processing systems , volume=
Diffusion models beat gans on image synthesis , author=. Advances in neural information processing systems , volume=
-
[161]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Structure-preserving super resolution with gradient guidance , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[162]
2021 , journal=
SD , author =. 2021 , journal=
2021
-
[163]
arXiv preprint arXiv:2409.17058 , year=
Degradation-guided one-step image super-resolution with diffusion priors , author=. arXiv preprint arXiv:2409.17058 , year=
-
[164]
Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part X 16 , pages=
Scene text image super-resolution in the wild , author=. Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part X 16 , pages=. 2020 , organization=
2020
-
[165]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Scene text telescope: Text-focused scene image super-resolution , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[166]
IEEE transactions on Image Processing , volume=
FSIM: A feature similarity index for image quality assessment , author=. IEEE transactions on Image Processing , volume=. 2011 , publisher=
2011
-
[167]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Blindly assess image quality in the wild guided by a self-adaptive hyper network , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[168]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
A text attention network for spatial deformation robust scene text image super-resolution , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[169]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Diffusion-based blind text image super-resolution , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[170]
European Conference on Computer Vision , pages=
DCDM: Diffusion-Conditioned-Diffusion Model for Scene Text Image Super-Resolution , author=. European Conference on Computer Vision , pages=. 2024 , organization=
2024
-
[171]
International journal of computer vision , volume=
The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale , author=. International journal of computer vision , volume=. 2020 , publisher=
2020
-
[172]
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
Single image super-resolution from transformed self-exemplars , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
-
[173]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Magic3d: High-resolution text-to-3d content creation , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[174]
arXiv preprint arXiv:2209.14988 , year=
Dreamfusion: Text-to-3d using 2d diffusion , author=. arXiv preprint arXiv:2209.14988 , year=
-
[175]
arXiv preprint arXiv:2305.16213 , year=
ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation , author=. arXiv preprint arXiv:2305.16213 , year=
-
[176]
arXiv preprint arXiv:2209.14792 , year=
Make-a-video: Text-to-video generation without text-video data , author=. arXiv preprint arXiv:2209.14792 , year=
-
[177]
Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation , author=. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
-
[178]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Human guided ground-truth generation for realistic image super-resolution , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[179]
Proceedings of the IEEE conference on computer vision and pattern recognition workshops , pages=
Enhanced deep residual networks for single image super-resolution , author=. Proceedings of the IEEE conference on computer vision and pattern recognition workshops , pages=
-
[180]
Proceedings of the European conference on computer vision (ECCV) , pages=
Image super-resolution using very deep residual channel attention networks , author=. Proceedings of the European conference on computer vision (ECCV) , pages=
-
[181]
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
Residual dense network for image super-resolution , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
-
[182]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Second-order attention network for single image super-resolution , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[183]
Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
Dual Aggregation Transformer for Image Super-Resolution , author=. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
-
[184]
IEEE Transactions on Pattern Analysis and Machine Intelligence , volume=
Image super-resolution via iterative refinement , author=. IEEE Transactions on Pattern Analysis and Machine Intelligence , volume=. 2022 , publisher=
2022
-
[185]
arXiv preprint arXiv:1503.02531 , year=
Distilling the knowledge in a neural network , author=. arXiv preprint arXiv:1503.02531 , year=
-
[186]
arXiv preprint arXiv:2305.08891 , year=
Common Diffusion Noise Schedules and Sample Steps are Flawed , author=. arXiv preprint arXiv:2305.08891 , year=
-
[187]
A Simple Framework for Open-Vocabulary Segmentation and Detection , author=
-
[188]
2014 , organization=
Microsoft coco: Common objects in context , author=. 2014 , organization=
2014
-
[189]
arXiv preprint arXiv:2010.02502 , year=
Denoising diffusion implicit models , author=. arXiv preprint arXiv:2010.02502 , year=
2010 arXiv
-
[190]
International Conference on Machine Learning , pages=
Fast sampling of diffusion models via operator learning , author=. International Conference on Machine Learning , pages=. 2023 , organization=
2023
-
[191]
Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
Q-diffusion: Quantizing diffusion models , author=. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
-
[192]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
On distillation of guided diffusion models , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[193]
arXiv preprint arXiv:2311.16518 , year=
SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution , author=. arXiv preprint arXiv:2311.16518 , year=
-
[194]
arXiv preprint arXiv:2404.01717 , year=
AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation , author=. arXiv preprint arXiv:2404.01717 , year=
-
[195]
Advances in Neural Information Processing Systems , volume=
Snips: Solving noisy inverse problems stochastically , author=. Advances in Neural Information Processing Systems , volume=
-
[196]
IEEE Transactions on Image Processing , volume=
FFDNet: Toward a fast and flexible solution for CNN-based image denoising , author=. IEEE Transactions on Image Processing , volume=. 2018 , publisher=
2018
-
[197]
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
Photo-realistic single image super-resolution using a generative adversarial network , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
-
[198]
arXiv preprint arXiv:2401.00877 , year=
Improving the Stability of Diffusion Models for Content Consistent Super-Resolution , author=. arXiv preprint arXiv:2401.00877 , year=
-
[199]
IEEE Transactions on Image Processing , year=
Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspective , author=. IEEE Transactions on Image Processing , year=
-
[200]
IEEE transactions on image processing , volume=
Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising , author=. IEEE transactions on image processing , volume=. 2017 , publisher=
2017
-
[201]
Proceedings of the European conference on computer vision (ECCV) workshops , pages=
Esrgan: Enhanced super-resolution generative adversarial networks , author=. Proceedings of the European conference on computer vision (ECCV) workshops , pages=
-
[202]
arXiv preprint arXiv:2309.05239 , year=
Hat: Hybrid attention transformer for image restoration , author=. arXiv preprint arXiv:2309.05239 , year=
-
[203]
arXiv preprint arXiv:2411.13383 , year=
Adversarial diffusion compression for real-world image super-resolution , author=. arXiv preprint arXiv:2411.13383 , year=
-
[204]
arXiv preprint arXiv:2501.05777 , year=
StructSR: Refuse Spurious Details in Real-World Image Super-Resolution , author=. arXiv preprint arXiv:2501.05777 , year=
-
[205]
arXiv preprint arXiv:2302.08453 , year=
T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models , author=. arXiv preprint arXiv:2302.08453 , year=
-
[206]
arXiv preprint arXiv:2312.09909 , year=
TMP: Temporal Motion Propagation for Online Video Super-Resolution , author=. arXiv preprint arXiv:2312.09909 , year=
-
[207]
IEEE Transactions on Image Processing , volume=
Text prior guided scene text image super-resolution , author=. IEEE Transactions on Image Processing , volume=. 2023 , publisher=
2023
-
[208]
Proceedings of the IEEE international conference on computer vision , pages=
Mask r-cnn , author=. Proceedings of the IEEE international conference on computer vision , pages=
-
[209]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , year=
UniVS: Unified and Universal Video Segmentation with Prompts as Queries , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , year=
-
[210]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[211]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
One-to-few label assignment for end-to-end dense detection , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[212]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , year=
Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , year=
-
[213]
Advances in Neural Information Processing Systems , volume=
Qlora: Efficient finetuning of quantized llms , author=. Advances in Neural Information Processing Systems , volume=
-
[214]
Proceedings of the Computer Vision and Pattern Recognition Conference , pages=
Toward generalized image quality assessment: Relaxing the perfect reference quality assumption , author=. Proceedings of the Computer Vision and Pattern Recognition Conference , pages=
-
[215]
arXiv preprint arXiv:2403.07319 , year=
Efficient Diffusion Model for Image Restoration by Residual Shifting , author=. arXiv preprint arXiv:2403.07319 , year=
-
[216]
arXiv preprint arXiv:1409.1556 , year=
Very deep convolutional networks for large-scale image recognition , author=. arXiv preprint arXiv:1409.1556 , year=
-
[217]
SSL: A Self-similarity Loss for Improving Generative Image Super-resolution , author=
-
[218]
Advances in neural information processing systems , volume=
Imagenet classification with deep convolutional neural networks , author=. Advances in neural information processing systems , volume=
-
[219]
Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14 , pages=
Perceptual losses for real-time style transfer and super-resolution , author=. Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14 , pages=. 2016 , organization=
2016
-
[220]
Advances in neural information processing systems , volume=
Generative adversarial nets , author=. Advances in neural information processing systems , volume=
-
[221]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Towards real-world blind face restoration with generative facial prior , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[222]
International conference on machine learning , pages=
Learning transferable visual models from natural language supervision , author=. International conference on machine learning , pages=. 2021 , organization=
2021
-
[223]
Advances in neural information processing systems , volume=
Visual instruction tuning , author=. Advances in neural information processing systems , volume=
-
[224]
IEEE transactions on image processing , volume=
Image super-resolution via sparse representation , author=. IEEE transactions on image processing , volume=. 2010 , publisher=
2010
-
[225]
The annals of probability , pages=
I-divergence geometry of probability distributions and minimization problems , author=. The annals of probability , pages=. 1975 , publisher=
1975
-
[226]
arXiv preprint arXiv:2403.14966 , year=
DreamFlow: High-Quality Text-to-3D Generation by Approximating Probability Flow , author=. arXiv preprint arXiv:2403.14966 , year=
-
[227]
arXiv preprint arXiv:2401.00909 , year=
Taming Mode Collapse in Score Distillation for Text-to-3D Generation , author=. arXiv preprint arXiv:2401.00909 , year=
-
[228]
arXiv preprint arXiv:1711.05101 , year=
Decoupled weight decay regularization , author=. arXiv preprint arXiv:1711.05101 , year=
-
[229]
arXiv preprint arXiv:2403.12036 , year=
One-Step Image Translation with Text-to-Image Models , author=. arXiv preprint arXiv:2403.12036 , year=
-
[230]
Advances in Neural Information Processing Systems , volume=
Towards robust blind face restoration with codebook lookup transformer , author=. Advances in Neural Information Processing Systems , volume=
-
[231]
Workshop on faces in'Real-Life'Images: detection, alignment, and recognition , year=
Labeled faces in the wild: A database forstudying face recognition in unconstrained environments , author=. Workshop on faces in'Real-Life'Images: detection, alignment, and recognition , year=
-
[232]
2019 IEEE international conference on image processing (ICIP) , pages=
Dense-haze: A benchmark for image dehazing with dense-haze and haze-free images , author=. 2019 IEEE international conference on image processing (ICIP) , pages=. 2019 , organization=
2019
-
[233]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Coser: Bridging image and language for cognitive super-resolution , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[234]
arXiv preprint arXiv:2311.05556 , year=
Lcm-lora: A universal stable-diffusion acceleration module , author=. arXiv preprint arXiv:2311.05556 , year=
-
[235]
Dong Chao and Loy Chen Change and He Kaiming and Tang Xiaoou , title =
-
[236]
European conference on computer vision , pages=
Accelerating the super-resolution convolutional neural network , author=. European conference on computer vision , pages=. 2016 , organization=
2016
-
[237]
Wang, Zhihao and Chen, Jian and Hoi, Steven C. H. , journal=. Deep Learning for Image Super-Resolution: A Survey , year=
-
[238]
IEEE Transactions on Pattern Analysis and Machine Intelligence , year=
Densely residual laplacian super-resolution , author=. IEEE Transactions on Pattern Analysis and Machine Intelligence , year=
-
[239]
Proceedings of the IEEE international conference on computer vision , pages=
Image super-resolution using dense skip connections , author=. Proceedings of the IEEE international conference on computer vision , pages=
-
[240]
Details or
Liang, Jie and Zeng, Hui and Zhang, Lei , booktitle=. Details or
-
[241]
What Hinders Perceptual Quality of
Xu, Tianshuo and Mi, Peng and Zheng, Xiawu and Li, Lijiang and Chao, Fei and Jiang, Guannan and Zhang, Wei and Zhou, Yiyi and Ji, Rongrong , journal=. What Hinders Perceptual Quality of
-
[242]
The 2018 PIRM Challenge on Perceptual Image Super-Resolution
Blau, Yochai and Mechrez, Roey and Timofte, Radu and Michaeli, Tomer and Zelnik-Manor, Lihi. The 2018 PIRM Challenge on Perceptual Image Super-Resolution. Computer Vision -- ECCV 2018 Workshops. 2019
2018
-
[243]
Proceedings of the IEEE/CVF International Conference on Computer Vision
Wang, Wei and Guo, Ruiming and Tian, Yapeng and Yang, Wenming , title =. Proceedings of the IEEE/CVF International Conference on Computer Vision
-
[244]
Proceedings of the European Conference on Computer Vision
Analyzing perception-distortion tradeoff using enhanced perceptual super-resolution network , author=. Proceedings of the European Conference on Computer Vision
-
[245]
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
Deep back-projection networks for super-resolution , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
-
[246]
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
Deeply-recursive convolutional network for image super-resolution , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
-
[247]
Liang, Jingyun and Cao, Jiezhang and Sun, Guolei and Zhang, Kai and Van Gool, Luc and Timofte, Radu , booktitle=. Swin
-
[248]
arXiv preprint arXiv:2203.06697 , year=
Efficient Long-Range Attention Network for Image Super-resolution , author=. arXiv preprint arXiv:2203.06697 , year=
-
[249]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
One-step diffusion with distribution matching distillation , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[250]
arXiv preprint arXiv:2403.05049 , year=
Xpsr: Cross-modal priors for diffusion-based image super-resolution , author=. arXiv preprint arXiv:2403.05049 , year=
-
[251]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Deep network interpolation for continuous imagery effect transition , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[252]
Proceedings of the IEEE/CVF international conference on computer vision , pages=
Real-esrgan: Training real-world blind super-resolution with pure synthetic data , author=. Proceedings of the IEEE/CVF international conference on computer vision , pages=
-
[253]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Repaint: Inpainting using denoising diffusion probabilistic models , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[254]
Wang, Xintao and Yu, Ke and Wu, Shixiang and Gu, Jinjin and Liu, Yihao and Dong, Chao and Qiao, Yu and Change Loy, Chen , booktitle=
-
[255]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Gan prior embedded network for blind face restoration in the wild , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[256]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Gcfsr: a generative and controllable face super resolution method without facial and gan priors , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[257]
Advances in neural information processing systems , volume=
Denoising diffusion probabilistic models , author=. Advances in neural information processing systems , volume=
-
[258]
Advances in Neural Information Processing Systems , volume=
Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps , author=. Advances in Neural Information Processing Systems , volume=
-
[259]
arXiv preprint arXiv:2309.02773 , year=
Diffusion model is secretly a training-free open vocabulary semantic segmenter , author=. arXiv preprint arXiv:2309.02773 , year=
-
[260]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Shadowdiffusion: When degradation prior meets diffusion model for shadow removal , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[261]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[262]
arXiv preprint arXiv:2308.09388 , year=
Diffusion Models for Image Restoration and Enhancement--A Comprehensive Survey , author=. arXiv preprint arXiv:2308.09388 , year=
-
[263]
arXiv preprint arXiv:2308.14469 , year=
Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization , author=. arXiv preprint arXiv:2308.14469 , year=
-
[264]
arXiv preprint arXiv:2308.15070 , year=
DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior , author=. arXiv preprint arXiv:2308.15070 , year=
-
[265]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
High-resolution image synthesis with latent diffusion models , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[266]
Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
Adding conditional control to text-to-image diffusion models , author=. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
-
[267]
Advances in neural information processing systems , volume=
Generating diverse high-fidelity images with vq-vae-2 , author=. Advances in neural information processing systems , volume=
-
[268]
arXiv e-prints , pages=
Improving the stability of diffusion models for content consistent super-resolution , author=. arXiv e-prints , pages=
-
[269]
IEEE Transactions on Pattern Analysis and Machine Intelligence , volume=
Interactive multi-dimension modulation for image restoration , author=. IEEE Transactions on Pattern Analysis and Machine Intelligence , volume=. 2021 , publisher=
2021
-
[270]
European Conference on Computer Vision , pages=
Metric learning based interactive modulation for real-world super-resolution , author=. European Conference on Computer Vision , pages=. 2022 , organization=
2022
-
[271]
arXiv preprint arXiv:2405.07913 , year=
CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models , author=. arXiv preprint arXiv:2405.07913 , year=
-
[272]
European Conference on Computer Vision , pages=
Scaledreamer: Scalable text-to-3d synthesis with asynchronous score distillation , author=. European Conference on Computer Vision , pages=. 2025 , organization=
2025
-
[273]
arXiv preprint arXiv:2207.12598 , year=
Classifier-free diffusion guidance , author=. arXiv preprint arXiv:2207.12598 , year=
-
[274]
arXiv preprint arXiv:2405.01536 , year=
Customizing Text-to-Image Models with a Single Image Pair , author=. arXiv preprint arXiv:2405.01536 , year=
-
[275]
The Twelfth International Conference on Learning Representations , year=
Text-to-3D with Classifier Score Distillation , author=. The Twelfth International Conference on Learning Representations , year=
-
[276]
European Conference on Computer Vision , pages=
Ziplora: Any subject in any style by effectively merging loras , author=. European Conference on Computer Vision , pages=. 2025 , organization=
2025
-
[277]
Proceedings of the IEEE/CVF international conference on computer vision , pages=
Swin transformer: Hierarchical vision transformer using shifted windows , author=. Proceedings of the IEEE/CVF international conference on computer vision , pages=
-
[278]
arXiv preprint arXiv:2010.11929 , year=
An image is worth 16x16 words: Transformers for image recognition at scale , author=. arXiv preprint arXiv:2010.11929 , year=
2010 arXiv
-
[279]
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , pages=
Lightweight non-local network for image super-resolution , author=. ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , pages=. 2021 , organization=
2021
-
[280]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Image super-resolution with non-local sparse attention , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[281]
arXiv preprint arXiv:2110.04627 , year=
Vector-quantized image modeling with improved vqgan , author=. arXiv preprint arXiv:2110.04627 , year=
-
[282]
arXiv preprint arXiv:2305.20049 , year=
A Unified Conditional Framework for Diffusion-based Image Restoration , author=. arXiv preprint arXiv:2305.20049 , year=
-
[283]
arXiv preprint arXiv:2303.08714 , year=
Resdiff: Combining cnn and diffusion model for image super-resolution , author=. arXiv preprint arXiv:2303.08714 , year=
-
[284]
arXiv preprint arXiv:2202.09671 , year=
Truncated diffusion probabilistic models and diffusion-based adversarial auto-encoders , author=. arXiv preprint arXiv:2202.09671 , year=
-
[285]
2023 , eprint=
Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approach , author=. 2023 , eprint=
2023
-
[286]
arXiv preprint arXiv:2306.04632 , year=
Designing a Better Asymmetric VQGAN for StableDiffusion , author=. arXiv preprint arXiv:2306.04632 , year=
-
[287]
arXiv preprint arXiv:2112.07804 , year=
Tackling the generative learning trilemma with denoising diffusion gans , author=. arXiv preprint arXiv:2112.07804 , year=
-
[288]
European conference on computer vision , pages=
Perceptual losses for real-time style transfer and super-resolution , author=. European conference on computer vision , pages=. 2016 , organization=
2016
-
[289]
The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003 , volume=
Multiscale structural similarity for image quality assessment , author=. The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003 , volume=. 2003 , organization=
2003
-
[290]
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
Perception prioritized training of diffusion models , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
-
[291]
arXiv preprint arXiv:2206.13397 , year=
Generative modelling with inverse heat dissipation , author=. arXiv preprint arXiv:2206.13397 , year=
-
[292]
Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
The perception-distortion tradeoff , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
-
[293]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Natural and realistic single image super-resolution with explicit natural manifold discrimination , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[294]
Sajjadi, Mehdi SM and Scholkopf, Bernhard and Hirsch, Michael , booktitle=. Enhance
-
[295]
Prashnani, Ekta and Cai, Hong and Mostofi, Yasamin and Sen, Pradeep , booktitle=. Pie
-
[296]
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Deep unfolding network for image super-resolution , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
-
[297]
Zhang, Wenlong and Liu, Yihao and Dong, Chao and Qiao, Yu , booktitle=. Rank
-
[298]
Li, Wenbo and Zhou, Kun and Qi, Lu and Lu, Liying and Lu, Jiangbo , booktitle=. Best-
-
[299]
Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
Fourier space losses for efficient perceptual image super-resolution , author=. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
-
[300]
Perception-Distortion Balanced
Zhang, Yuehan and Ji, Bo and Hao, Jia and Yao, Angela , booktitle=. Perception-Distortion Balanced. 2022 , organization=
2022
Reviewed August 1, 2026 · model on record in the stance chip above.
Discussion (0). Continue with ORCID to comment.