Pith. sign in

REVIEW 46 cited by

Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2212.00490 v2 pith:XQEYLUXJ submitted 2022-12-01 cs.CV

Yinhuai Wang , Jiwen Yu , Jian Zhang This is my paper · ORCID
classification cs.CV
keywords ddnmrestorationdiffusionimagemodelnull-spacezero-shotdenoising
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Most existing Image Restoration (IR) models are task-specific, which can not be generalized to different degradation operators. In this work, we propose the Denoising Diffusion Null-Space Model (DDNM), a novel zero-shot framework for arbitrary linear IR problems, including but not limited to image super-resolution, colorization, inpainting, compressed sensing, and deblurring. DDNM only needs a pre-trained off-the-shelf diffusion model as the generative prior, without any extra training or network modifications. By refining only the null-space contents during the reverse diffusion process, we can yield diverse results satisfying both data consistency and realness. We further propose an enhanced and robust version, dubbed DDNM+, to support noisy restoration and improve restoration quality for hard tasks. Our experiments on several IR tasks reveal that DDNM outperforms other state-of-the-art zero-shot IR methods. We also demonstrate that DDNM+ can solve complex real-world applications, e.g., old photo restoration.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 46 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps

    cs.LG 2025-01 reject novelty 7.0 of 10

    A volume-preserving reparameterization makes the likelihood of cascaded diffusion models exactly computable, giving state-of-the-art density estimation on standard image benchmarks.

  2. Multimodal Spatiotemporal Atmospheric Data Assimilation with Latent Video Flow-matching

    cs.LG 2026-08 conditional novelty 6.0 of 10

    A single latent video flow-matching prior, with posterior guidance, performs super-resolution, multimodal data fusion, filtering/smoothing, and observation-to-forecast for the global atmosphere using real station obse...

  3. From Sparse X-rays to 3D CT: Training-Free Reconstruction with Diffusion Priors

    eess.IV 2026-06 unverdicted novelty 6.0 of 10

    TF-PRDiT uses a frozen 3D diffusion transformer prior with task-specific forward operators and predictor-corrector sampling to solve X-ray-to-CT reconstruction and other volumetric inverse problems without any retraining.

  4. Semantic-Guided Cross-Sensor Super Resolution of Remote Sensing Images: A Gated Dual Conditioning Flow Matching Model

    cs.CV 2025-10 conditional novelty 6.0 of 10

    A gated dual-conditioning flow-matching model achieves 10 m→2 m cross-sensor super-resolution with a 38% FID reduction over the best baseline on a rare-landform (retrogressive thaw slump) benchmark.

  5. A novel method and dataset for depth-guided image deblurring from smartphone Lidar

    eess.IV 2025-09 conditional novelty 6.0 of 10

    Lidar depth-guided deblurring via a zero-shot diffusion method, evaluated on a new 45-scene dataset, achieves the best perceptual quality (LPIPS).

  6. Zero-shot CT Super-Resolution using Diffusion-based 2D Projection Priors and Signed 3D Gaussians

    eess.IV 2025-08 conditional novelty 6.0 of 10

    A two-stage zero-shot CT super-resolution framework that upscales 2D X-ray projections with a diffusion prior and reconstructs the 3D volume using negative-density 3D Gaussian splatting.

  7. GuidPaint: Class-Guided Image Inpainting with Diffusion Models

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A training-free inpainting method that uses classifier gradients to guide masked region content toward a target class, with hybrid sampling for coherence.

  8. Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A transfer training scheme converts Stable Diffusion's 8x VAE into a 4x VAE that stays compatible with the pretrained UNet, improving fine-structure preservation in real-world super-resolution at lower FLOPs.

  9. 4KAgent: Agentic Any Image to 4K Super-Resolution

    cs.CV 2025-07 reject novelty 6.0 of 10

    An agentic pipeline that plans and executes image restoration from a toolbox of pretrained models to upscale arbitrary images to 4K, reporting state-of-the-art results on many benchmarks.

  10. FRIDU: Functional Map Refinement with Guided Image Diffusion

    cs.CV 2025-06 conditional novelty 6.0 of 10

    FRIDU refines functional maps by treating them as images and applying a conditional diffusion model with point-to-point and geometric guidance at inference.

  11. DarkDiff: Advancing Low-Light Raw Enhancement by Retasking Diffusion Models for Camera ISP

    cs.CV 2025-05 conditional novelty 6.0 of 10

    DarkDiff fine-tunes Stable Diffusion with region-based cross-attention, a residual VAE, and a pixel-space loss to turn noisy linear-RGB low-light images into clean sRGB photos, achieving top LPIPS on SID, ELD, and LRD.

  12. Coding-Prior Guided Diffusion Network for Video Deblurring

    cs.CV 2025-04 conditional novelty 6.0 of 10

    A two-stage network that fuses video codec motion vectors and residuals with a diffusion model improves no-reference perceptual scores on GoPro and DVD, while PSNR and SSIM fall far below existing methods.

  13. Unpaired Deblurring via Decoupled Diffusion Model

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A diffusion model that decouples structural features from blur patterns using unpaired target-domain images can deblur photos in unseen domains without paired training data.

  14. Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior

    cs.CV 2025-01 conditional novelty 6.0 of 10

    The paper provides evidence that Diffusion Posterior Sampling implicitly maximizes a posterior rather than sampling the posterior, and uses this to build faster, better-performing restoration algorithms.

  15. CDI: Blind Image Restoration Fidelity Evaluation based on Consistency with Degraded Image

    eess.IV 2025-01 conditional novelty 6.0 of 10

    CDI is a wavelet-domain fidelity metric for blind image restoration that compares restored images with the degraded input rather than the reference, plus a reference-free variant and a new subjective dataset.

  16. Proxies for Distortion and Consistency with Applications for Real-World Image Restoration

    cs.CV 2025-01 conditional novelty 6.0 of 10

    The paper introduces degradation-estimation-based proxies for MSE, LPIPS, and consistency so that real-world image restoration methods can be ranked without ground truth.

  17. Navigating Image Restoration with VAR's Distribution Alignment Prior

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A unified image restoration framework, VarFormer, repurposes the scale-wise latent features of the pretrained generative model VAR as a distribution-alignment prior and reports state-of-the-art results across six degr...

  18. An Ordinary Differential Equation Sampler with Stochastic Start for Diffusion Bridge Models

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A stochastic-start ODE sampler for diffusion bridge models avoids the singular start of the probability-flow ODE and beats prior samplers with fewer neural network evaluations.

  19. Beyond Pixels: Text Enhances Generalization in Real-World Image Restoration

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A restoration-specific captioner that adaptively generates detailed text descriptions improves the generalization of text-to-image diffusion models on real-world image restoration.

  20. TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution

    cs.CV 2024-11 conditional novelty 6.0 of 10

    TSD-SR distills a multi-step diffusion model into a one-step super-resolution model via Target Score Distillation and trajectory sampling, giving fast inference with perceptual quality competitive with multi-step methods.

  21. Enhancing Diffusion Posterior Sampling for Inverse Problems by Integrating Crafted Measurements

    cs.CV 2024-11 conditional novelty 6.0 of 10

    DPS-CM improves diffusion posterior sampling for inverse problems by generating a denoised reverse-measurement trajectory and using it in the likelihood gradient, yielding better restoration in experiments.

  22. Provable diffusion-based posterior sampling for linear inverse problems via DDIM

    cs.LG 2026-07 reject novelty 5.0 of 10

    A SVD-based, coordinate-wise DDIM sampler is claimed to asymptotically sample from the posterior for noisy linear inverse problems, but the proof's posterior identification step does not follow from the stated updates.

  23. Diffusion-Based Noise-Adaptive Null-Space Channel Estimation for OFDM Systems

    cs.IT 2026-07 conditional novelty 5.0 of 10

    A diffusion estimator with noise-adaptive null-space correction recovers sparse-pilot OFDM channels at lower NMSE than MMSE, toolbox, DPS, and DMPS baselines on 5G TDL/CDL simulations.

  24. Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models

    cs.LG 2025-08 conditional novelty 5.0 of 10

    A funnel-shaped particle schedule and an adaptive temperature schedule improve SMC-based inference-time scaling for text-to-image diffusion models at fixed compute.

  25. DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A training-free diffusion-guidance framework that couples scale alignment across windows and geometric multi-view constraints inside the denoising loop yields more scale- and geometry-consistent depth for long videos.

  26. Time-variant Image Inpainting via Interactive Distribution Transition Estimation

    cs.CV 2025-06 conditional novelty 5.0 of 10

    The authors introduce time-variant image inpainting (TAMP), a benchmark (TAMP-Street), and InDiTE-Diff, a diffusion-based method with a semantic complementation module that outperforms prior reference-guided inpaintin...

  27. Reversing Flow for Image Restoration

    cs.CV 2025-06 conditional novelty 5.0 of 10

    ResFlow models HQ-to-LQ degradation as a deterministic augmented flow and inverts it via velocity matching, reporting state-of-the-art restoration in fewer than four sampling steps.

  28. Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A weighted-particle sampler evolves the posterior through the diffusion model's reverse dynamics, with theoretical error bounds and improved image reconstructions.

  29. Dual Prompting Image Restoration with Diffusion Transformers

    cs.CV 2025-04 conditional novelty 5.0 of 10

    DPIR combines lightweight conditioning with global-local CLIP visual prompts and T5 text in an SD3 diffusion transformer to improve image restoration quality.

  30. Satellite Observations Guided Diffusion Model for Accurate Meteorological States at Arbitrary Resolution

    cs.LG 2025-02 reject novelty 5.0 of 10

    A satellite-conditioned diffusion model with station-guided sampling is claimed to downscale ERA5 weather fields to 6.25 km more accurately than existing methods, but the evaluation is circular.

  31. Diffusion Prior Interpolation for Flexibility Real-World Face Super-Resolution

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A diffusion-based face super-resolution method using fixed and random masks plus a trained corrector network reports state-of-the-art perceptual quality and face recognition consistency on common benchmarks.

  32. Enhancing and Accelerating Diffusion-Based Inverse Problem Solving through Measurements Optimization

    cs.CV 2024-12 conditional novelty 5.0 of 10

    Measurements Optimization, which alternates SGLD steps on the measurement objective with denoiser projection, achieves SOTA or near-SOTA image restoration at 50-100 diffusion NFEs across eight linear and nonlinear tasks.

  33. Diffusion Models Meet Network Management: Improving Traffic Matrix Analysis with Diffusion-based Approach

    cs.NI 2024-11 conditional novelty 5.0 of 10

    Diffusion-TM combines a pretrained diffusion model with measurement-gradient guidance and a two-stage missing-data training scheme to estimate, complete, and synthesize network traffic matrices.

  34. Constrained Diffusion with Trust Sampling

    cs.LG 2024-11 conditional novelty 5.0 of 10

    Trust Sampling improves training-free constrained diffusion by allowing multiple normalized gradient steps per denoising timestep, with a variance-based trust schedule and a predicted-noise manifold boundary for early...

  35. Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution

    cs.CV 2026-07 reject novelty 4.0 of 10

    DDR-SR routes each real-world low-resolution image to one of two diffusion experts based on a high-frequency-loss difficulty score, using a low-compression VAE for hard images and a high-compression VAE for easy image...

  36. Generative Spectrum Cartography: Unified Reconstruction and Active Sensing via Diffusion Models

    cs.IT 2025-12 conditional novelty 4.0 of 10

    A diffusion-based framework reconstructs spectrum maps and guides where to sample next using closed-form Bayesian updates for linear and quantized measurements.

  37. Local MAP Sampling for Diffusion Models

    cs.GR 2025-10 conditional novelty 4.0 of 10

    LMAPS frames reverse-diffusion inverse-problem solving as repeated local MAP estimation, unifying existing optimization-based solvers, and achieves strong PSNR gains on tasks like motion deblurring, JPEG restoration, ...

  38. InfraDiffusion: zero-shot depth map restoration with diffusion models and prompted segmentation from sparse infrastructure point clouds

    cs.CV 2025-09 reject novelty 4.0 of 10

    InfraDiffusion adapts DDNM with boundary masks to restore depth maps from masonry point clouds, reporting large SAM-based brick-segmentation improvements, but the evaluation protocol appears to ground the masks in the...

  39. Multi-Step Guided Diffusion for Image Restoration on Edge Devices: Toward Lightweight Perception in Embodied AI

    cs.CV 2025-06 reject novelty 4.0 of 10

    Applying multiple guidance gradient updates per denoising step improves LPIPS and PSNR for super-resolution and deblurring on natural and aerial images, and runs in real time on a Jetson Orin Nano, though the per-step...

  40. DiffuseSlide: Training-Free High Frame Rate Video Generation Diffusion

    cs.CV 2025-06 conditional novelty 4.0 of 10

    DiffuseSlide boosts the frame rate of latent diffusion videos via latent interpolation, noise re-injection, and sliding-window denoising, reporting better FVD, PSNR, and SSIM than several baselines on WebVid-10M.

  41. MODS: Multi-source Observations Conditional Diffusion Model for Meteorological State Downscaling

    physics.ao-ph 2025-06 reject novelty 4.0 of 10

    A multi-source satellite-conditioned diffusion model for ERA5 downscaling reports improved station-level metrics, but the evaluation is compromised because station observations are used as sampling guidance and as the...

  42. Frequency-Aware Guidance for Blind Image Restoration via Diffusion Models

    cs.CV 2024-11 conditional novelty 4.0 of 10

    A plug-and-play wavelet frequency guidance loss improves blind image restoration in diffusion models, giving up to 3.72 dB PSNR gain on motion deblurring.

  43. Text to Image Generation and Editing: A Survey

    cs.CV 2025-05 conditional novelty 3.0 of 10

    A broad survey of text-to-image generation and editing research from 2021 to 2024, organized by architecture and comparison tables.

  44. Zero-Shot Low-Light Image Enhancement via Joint Frequency Domain Priors Guided Diffusion

    cs.CV 2024-11 conditional novelty 3.0 of 10

    A zero-shot low-light image enhancement method that injects joint wavelet and Fourier frequency priors into a pre-trained ImageNet diffusion model, reporting top zero-shot metrics on LOL and SICE.

  45. Plug-and-play Diffusion Models for Image Compressive Sensing with Data Consistency Projection

    cs.CV 2025-09 reject novelty 2.0 of 10

    A linear average of GAP and HQS data-consistency updates during DDIM sampling is proposed, but it reduces to a single scaled projection when the sensing matrix is orthogonal.

  46. Projection-Based Correction for Enhancing Deep Inverse Networks

    cs.LG 2025-05 conditional novelty 2.0 of 10

    A projection step that forces a deep network's reconstruction to satisfy y = Ax gives small PSNR gains in low-noise imaging tests, but the supporting theory is a restatement of the definition of a well-trained network.

Pith tools