pith. sign in

arxiv: 2606.19097 · v1 · pith:RRO5G67Jnew · submitted 2026-06-17 · 💻 cs.CV

DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration

Yanjie Tu , Qingsen Yan , Axi Niu , Tao Hu , Haokui Zhang , Jiantao Zhou This is my paper

Pith reviewed 2026-06-26 21:23 UTC · model grok-4.3

classification 💻 cs.CV
keywords image restorationall-in-one restorationdeep unfoldingvisual priorsdegradation modelingDINOhalf-quadratic splitting
0
0 comments X

The pith

DVANet unifies image restoration across diverse degradations by unfolding a process with degradation-aware consistency and DINOv3 visual priors.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces DVANet to create a unified framework for restoring images affected by various degradation types. It models the restoration as an iterative process inspired by half-quadratic splitting, splitting it into a degradation-aware branch that extracts and conditions on degradation cues, and a reconstruction branch that uses DINOv3 to supply missing structural and semantic details. This addresses the black-box nature of end-to-end methods and the inflexibility of prior deep unfolding approaches. The result is improved adaptability and performance across multiple degradation scenarios and domains.

Core claim

DVANet formulates unified image restoration under complex degradations as a collaborative unfolding process between degradation-aware observation consistency and visual-prior-guided reconstruction, where a degradation representation module extracts global and local cues for conditioned mapping, and DINOv3 provides hierarchical priors to recover details in damaged regions.

What carries the argument

A deep unfolding network based on half-quadratic splitting with a degradation-aware observation consistency branch using a degradation representation module and conditioned mapping, paired with a visual-prior-guided reconstruction branch employing DINOv3.

If this is right

  • DVANet demonstrates superior or competitive performance on multi-scenario degradation tasks.
  • It exhibits favorable degradation adaptability through the degradation-conditioned mapping.
  • The use of visual priors improves structural detail recovery in locally damaged content.
  • It shows good generalization ability on cross-domain image restoration tasks.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This could suggest that foundation model priors like DINOv3 are broadly useful for inverse imaging problems.
  • Future work might explore replacing DINOv3 with other vision models to test robustness.
  • The collaborative unfolding might apply to related tasks like denoising or super-resolution in a unified way.

Load-bearing premise

That the visual priors from DINOv3 effectively complement missing structural information in damaged image regions.

What would settle it

A test showing that removing the DINOv3 branch or replacing it with random priors yields equivalent or better restoration performance on benchmark datasets with local damages.

Figures

Figures reproduced from arXiv: 2606.19097 by Axi Niu, Haokui Zhang, Jiantao Zhou, Qingsen Yan, Tao Hu, Yanjie Tu.

Figure 1
Figure 1. Figure 1: Conceptual comparison of task-specific restoration, existing All [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overall architecture of DVANet. Given a degraded image, DVANet extracts two types of auxiliary cues: (a) global-local degradation representations [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: (a) Degradation-conditioned data mapping guides the observation [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Visual comparison of DVANet with state-of-the-art methods on the HQ-NightRain dataset, including the raindrop (RD) subset and the rain-streak [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Visual comparison of DVANet with state-of-the-art methods on the CDD11 dataset under composite degradation settings. The first, second, and third [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 7
Figure 7. Figure 7: Validation PSNR curves of different prior ablation variants on the [PITH_FULL_IMAGE:figures/full_fig_p010_7.png] view at source ↗
read the original abstract

All-in-One image restoration aims to develop a unified restoration framework for handling diverse degradation types. Existing end-to-end methods usually regard the restoration process as a black-box mapping, lacking an explicit optimization interpretation. Although deep unfolding provides an interpretable iterative modeling paradigm for image restoration, existing methods mostly rely on fixed degradation assumptions or predefined degradation information, making them difficult to adapt to unified restoration requirements under complex degradations and locally damaged content. This limitation restricts their performance in degradation suppression and structural detail recovery. To address these issues, this paper proposes DVANet, a deep unfolding network inspired by the half-quadratic splitting optimization algorithm, which formulates unified image restoration under complex degradations as a collaborative unfolding process between degradation-aware observation consistency and visual-prior-guided reconstruction. Specifically, in the degradation-aware observation consistency branch, a degradation representation module is employed to extract global degradation attributes and local degradation cues, and degradation-conditioned mapping is used to enhance the model's adaptability to different degradation types. In the visual-prior-guided reconstruction branch, DINOv3 is introduced to provide structural and semantic information as hierarchical visual priors, thereby complementing the missing structural information in damaged regions and improving detail recovery. Extensive experiments demonstrate that DVANet achieves superior or competitive performance on multi-scenario degradation and cross-domain image restoration tasks, showing favorable degradation adaptability and generalization ability.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper proposes DVANet, a deep unfolding network for all-in-one image restoration under complex degradations, formulated via half-quadratic splitting as a collaborative process between a degradation-aware observation consistency branch (using a degradation representation module and degradation-conditioned mapping) and a visual-prior-guided reconstruction branch (introducing DINOv3 to supply hierarchical structural and semantic priors for damaged regions). It claims superior or competitive performance with favorable adaptability and generalization on multi-scenario degradation and cross-domain tasks.

Significance. If the central claims hold, the work would advance interpretable deep-unfolding methods for unified restoration by explicitly modeling degradation adaptability alongside visual priors, potentially addressing limitations of black-box end-to-end approaches and fixed-assumption unfolding baselines.

major comments (1)
  1. [visual-prior-guided reconstruction branch] The visual-prior-guided reconstruction branch (described in the abstract) assumes DINOv3 supplies effective hierarchical priors that complement missing content in locally damaged regions and remain informative under heavy degradation, yet provides no mechanism for injection into HQS unfolding iterations or alignment with the degradation-aware branch; this is load-bearing for the claimed advantage of the collaborative formulation over standard deep-unfolding methods.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive comment regarding the integration mechanism in the visual-prior-guided reconstruction branch. We address this point directly below and clarify the collaborative formulation.

read point-by-point responses

  1. Referee: [visual-prior-guided reconstruction branch] The visual-prior-guided reconstruction branch (described in the abstract) assumes DINOv3 supplies effective hierarchical priors that complement missing content in locally damaged regions and remain informative under heavy degradation, yet provides no mechanism for injection into HQS unfolding iterations or alignment with the degradation-aware branch; this is load-bearing for the claimed advantage of the collaborative formulation over standard deep-unfolding methods.

    Authors: The manuscript does describe the injection and alignment mechanism in Section 3. The overall HQS formulation (Eq. 3) alternates between the two subproblems solved by the respective branches. The degradation-aware observation consistency branch produces an intermediate estimate that is passed as input to the visual-prior-guided reconstruction branch at each unfolding iteration; the output of the reconstruction branch is then fed back to update the auxiliary variable in the next iteration. DINOv3 hierarchical features are injected by feature concatenation at multiple scales inside the reconstruction network (detailed in Section 3.3 and Figure 3). This explicit alternation constitutes the alignment between branches. We acknowledge that the description could be more explicit to prevent misreading and will add a short clarifying paragraph plus an additional equation highlighting the cross-branch information flow in the revised version. revision: partial

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper presents DVANet as an explicit architectural design choice: a deep-unfolding network based on HQS that splits restoration into a degradation-aware branch (with explicit modules for global/local degradation cues) and a visual-prior branch (injecting DINOv3 features). These are modeling decisions, not derived predictions. Performance claims rest on experimental results across datasets rather than any fitted parameter being renamed as a prediction or any self-citation chain that reduces the central formulation to its own inputs. No equations or steps in the provided description exhibit self-definition, ansatz smuggling, or renaming of known results. The derivation is self-contained as a proposed network structure validated empirically.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available, providing no specific details on free parameters, axioms, or invented entities beyond high-level network components.

pith-pipeline@v0.9.1-grok · 5786 in / 1027 out tokens · 56660 ms · 2026-06-26T21:23:58.300652+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

111 extracted references · 10 canonical work pages · 2 internal anchors

  1. [1]

    Learning continuous wasser- stein barycenter space for generalized all-in-one image restoration,

    X. Tang, X. He, J. Xu, X. Gu, and J. Sun, “Learning continuous wasser- stein barycenter space for generalized all-in-one image restoration,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026

    2026

  2. [2]

    Bio-inspired image restoration,

    Y . Cui, W. Ren, and A. Knoll, “Bio-inspired image restoration,” Advances in Neural Information Processing Systems, vol. 38, pp. 80 452–80 481, 2026

    2026

  3. [3]

    Adaptive dynamic filtering network for image denoising,

    H. Shen, Z.-Q. Zhao, and W. Zhang, “Adaptive dynamic filtering network for image denoising,” inProceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 2, 2023, pp. 2227–2235

    2023

  4. [4]

    Strip- former: Strip transformer for fast image deblurring,

    F.-J. Tsai, Y .-T. Peng, Y .-Y . Lin, C.-C. Tsai, and C.-W. Lin, “Strip- former: Strip transformer for fast image deblurring,” inEuropean conference on computer vision. Springer, 2022, pp. 146–162

    2022

  5. [5]

    Learning a sparse transformer net- work for effective image deraining,

    X. Chen, H. Li, M. Li, and J. Pan, “Learning a sparse transformer net- work for effective image deraining,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023, pp. 5896–5905

    2023

  6. [6]

    Vision transformers for single image dehazing,

    Y . Song, Z. He, H. Qian, and X. Du, “Vision transformers for single image dehazing,”IEEE Trans. Image Process., vol. 32, pp. 1927–1941, 2023

    1927

  7. [7]

    Retinex- former: One-stage retinex-based transformer for low-light image en- hancement,

    Y . Cai, H. Bian, J. Lin, H. Wang, R. Timofte, and Y . Zhang, “Retinex- former: One-stage retinex-based transformer for low-light image en- hancement,” inProceedings of the IEEE/CVF international conference on computer vision, 2023, pp. 12 504–12 513

    2023

  8. [8]

    Image restoration with mean-reverting stochastic differential equations,

    Z. Luo, F. K. Gustafsson, Z. Zhao, J. Sj ¨olund, and T. B. Sch¨on, “Image restoration with mean-reverting stochastic differential equations,”arXiv preprint arXiv:2301.11699, 2023

    work page arXiv 2023

  9. [9]

    Fourmer: An efficient global modeling paradigm for image restoration,

    M. Zhou, J. Huang, C.-L. Guo, and C. Li, “Fourmer: An efficient global modeling paradigm for image restoration,” inInternational conference on machine learning. PMLR, 2023, pp. 42 589–42 601

    2023

  10. [10]

    Revitalizing convolutional network for image restoration,

    Y . Cui, W. Ren, X. Cao, and A. Knoll, “Revitalizing convolutional network for image restoration,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, pp. 9423–9438, 2024

    2024

  11. [11]

    Mb-taylorformer v2: Improved multi-branch linear transformer expanded by taylor formula for image restoration,

    Z. Jin, Y . Qiu, K. Zhang, H. Li, and W. Luo, “Mb-taylorformer v2: Improved multi-branch linear transformer expanded by taylor formula for image restoration,”IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

    2025

  12. [12]

    Deep unfolding network for image super-resolution,

    K. Zhang, L. V . Gool, and R. Timofte, “Deep unfolding network for image super-resolution,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 3217–3226

    2020

  13. [13]

    Deep generalized unfolding networks for image restoration,

    C. Mou, Q. Wang, and J. Zhang, “Deep generalized unfolding networks for image restoration,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 17 399–17 410

    2022

  14. [14]

    Learning proximal operators: Using denoising networks for regularizing inverse imaging problems,

    T. Meinhardt, M. Moller, C. Hazirbas, and D. Cremers, “Learning proximal operators: Using denoising networks for regularizing inverse imaging problems,” inProceedings of the IEEE international confer- ence on computer vision, 2017, pp. 1781–1790

    2017

  15. [15]

    Vision-language gradient descent-driven all-in-one deep unfolding networks,

    H. Zeng, X. Wang, Y . Chen, J. Su, and J. Liu, “Vision-language gradient descent-driven all-in-one deep unfolding networks,” inProceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 7524–7533

    2025

  16. [16]

    Image denoising by sparse 3-d transform-domain collaborative filtering,

    K. Dabov, A. Foi, V . Katkovnik, and K. Egiazarian, “Image denoising by sparse 3-d transform-domain collaborative filtering,”IEEE Trans- actions on image processing, vol. 16, no. 8, pp. 2080–2095, 2007

    2080

  17. [17]

    Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization,

    W. Dong, L. Zhang, G. Shi, and X. Wu, “Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization,”IEEE Transactions on image processing, vol. 20, no. 7, pp. 1838–1857, 2011

    2011

  18. [18]

    All-in-one image restoration for unknown corruption,

    B. Li, X. Liu, P. Hu, Z. Wu, J. Lv, and X. Peng, “All-in-one image restoration for unknown corruption,” inProc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2022, pp. 17 452–17 462

    2022

  19. [19]

    Promp- tir: Prompting for all-in-one image restoration,

    V . Potlapalli, S. W. Zamir, S. H. Khan, and F. Shahbaz Khan, “Promp- tir: Prompting for all-in-one image restoration,”Advances in neural information processing systems, vol. 36, pp. 71 275–71 293, 2023

    2023

  20. [20]

    Denoising prior driven deep neural network for image restoration,

    W. Dong, P. Wang, W. Yin, G. Shi, F. Wu, and X. Lu, “Denoising prior driven deep neural network for image restoration,”IEEE transactions on pattern analysis and machine intelligence, vol. 41, no. 10, pp. 2305– 2318, 2018

    2018

  21. [21]

    Half-quadratic-based iterative minimization for robust sparse representation,

    R. He, W.-S. Zheng, T. Tan, and Z. Sun, “Half-quadratic-based iterative minimization for robust sparse representation,”IEEE transactions on pattern analysis and machine intelligence, vol. 36, no. 2, pp. 261–275, 2013

    2013

  22. [22]

    DINOv3

    O. Sim ´eoni, H. V . V o, M. Seitzer, F. Baldassarre, M. Oquab, C. Jose, V . Khalidov, M. Szafraniec, S. Yi, M. Ramamonjisoaet al., “Dinov3,” arXiv preprint arXiv:2508.10104, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  23. [23]

    Ingredient-oriented multi-degradation learning for image restoration,

    J. Zhang, J. Huang, M. Yao, Z. Yang, H. Yu, M. Zhou, and F. Zhao, “Ingredient-oriented multi-degradation learning for image restoration,” inProc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2023, pp. 5825–5835

    2023

  24. [24]

    Visual-in-visual: A unified and efficient baseline for image restoration,

    Y . Cui, W. Ren, B. Shi, and A. Knoll, “Visual-in-visual: A unified and efficient baseline for image restoration,”IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026

    2026

  25. [25]

    Prores: Exploring degradation-aware visual prompt for universal image restora- tion,

    J. Ma, T. Cheng, G. Wang, Q. Zhang, X. Wang, and L. Zhang, “Prores: Exploring degradation-aware visual prompt for universal image restora- tion,”arXiv preprint arXiv:2306.13653, 2023

    work page arXiv 2023

  26. [26]

    Neural degradation representation learning for all-in-one image restoration,

    M. Yao, R. Xu, Y . Guan, J. Huang, and Z. Xiong, “Neural degradation representation learning for all-in-one image restoration,”IEEE trans- actions on image processing, vol. 33, pp. 5408–5423, 2024

    2024

  27. [27]

    Instructir: High-quality im- age restoration following human instructions,

    M. V . Conde, G. Geigle, and R. Timofte, “Instructir: High-quality im- age restoration following human instructions,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 1–21

    2024

  28. [28]

    Uniprocessor: a text- induced unified low-level image processor,

    H. Duan, X. Min, S. Wu, W. Shen, and G. Zhai, “Uniprocessor: a text- induced unified low-level image processor,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 180–199

    2024

  29. [29]

    Complexity experts are task-discriminative learners for any image restoration,

    E. Zamfir, Z. Wu, N. Mehta, Y . Tan, D. P. Paudel, Y . Zhang, and R. Timofte, “Complexity experts are task-discriminative learners for any image restoration,” inProceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 12 753–12 763

    2025

  30. [30]

    Controlling vision-language models for universal image restoration,

    Z. Luo, F. K. Gustafsson, Z. Zhao, J. Sj ¨olund, and T. B. Sch ¨on, “Controlling vision-language models for universal image restoration,” arXiv preprint arXiv:2310.01018, 2023

    work page arXiv 2023

  31. [31]

    Multi- task image restoration guided by robust dino features,

    X. Lin, C. Ren, K. C. Chan, L. Qi, J. Pan, and M.-H. Yang, “Multi- task image restoration guided by robust dino features,”arXiv preprint arXiv:2312.01677, 2023

    work page arXiv 2023

  32. [32]

    Deepsn-net: Deep semi-smooth newton driven network for blind image restoration,

    X. Deng, C. Zhang, L. Jiang, J. Xia, and M. Xu, “Deepsn-net: Deep semi-smooth newton driven network for blind image restoration,”IEEE JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 12 Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 4, pp. 2632–2646, 2025

    2021

  33. [33]

    Learning fast approximations of sparse coding,

    K. Gregor and Y . LeCun, “Learning fast approximations of sparse coding,” inProceedings of the 27th international conference on in- ternational conference on machine learning, 2010, pp. 399–406

    2010

  34. [34]

    A fast iterative shrinkage-thresholding algorithm for linear inverse problems,

    A. Beck and M. Teboulle, “A fast iterative shrinkage-thresholding algorithm for linear inverse problems,”SIAM journal on imaging sciences, vol. 2, no. 1, pp. 183–202, 2009

    2009

  35. [35]

    Distributed optimization and statistical learning via the alternating direction method of multi- pliers,

    P. Neal, C. Eric, P. Borja, and E. Jonathan, “Distributed optimization and statistical learning via the alternating direction method of multi- pliers,”Foundations and Trends® in Machine learning, vol. 3, no. 1, pp. 1–122, 2011

    2011

  36. [36]

    Deep convolutional dictionary learning for image denoising,

    H. Zheng, H. Yong, and L. Zhang, “Deep convolutional dictionary learning for image denoising,” inProceedings of the IEEE/CVF con- ference on computer vision and pattern recognition, 2021, pp. 630–641

    2021

  37. [37]

    Desnownet: Context-aware deep network for snow removal,

    Y .-F. Liu, D.-W. Jaw, S.-C. Huang, and J.-N. Hwang, “Desnownet: Context-aware deep network for snow removal,”IEEE Transactions on Image Processing, vol. 27, no. 6, pp. 3064–3073, 2018

    2018

  38. [38]

    Jstasr: Joint size and transparency-aware snow removal algorithm based on modified partial convolution and veiling effect removal,

    W.-T. Chen, H.-Y . Fang, J.-J. Ding, C.-C. Tsai, and S.-Y . Kuo, “Jstasr: Joint size and transparency-aware snow removal algorithm based on modified partial convolution and veiling effect removal,” inEuropean conference on computer vision. Springer, 2020, pp. 754–770

    2020

  39. [39]

    All snow removed: Single image desnowing algo- rithm using hierarchical dual-tree complex wavelet representation and contradict channel loss,

    W.-T. Chen, H.-Y . Fang, C.-L. Hsieh, C.-C. Tsai, I. Chen, J.-J. Ding, S.-Y . Kuoet al., “All snow removed: Single image desnowing algo- rithm using hierarchical dual-tree complex wavelet representation and contradict channel loss,” inProceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 4196–4205

    2021

  40. [40]

    A database of human seg- mented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics,

    D. Martin, C. Fowlkes, D. Tal, and J. Malik, “A database of human seg- mented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics,” inProc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), vol. 2, 2001, pp. 416–423

    2001

  41. [41]

    Dense-haze: A benchmark for image dehazing with dense-haze and haze-free images,

    C. O. Ancuti, C. Ancuti, M. Sbert, and R. Timofte, “Dense-haze: A benchmark for image dehazing with dense-haze and haze-free images,” in2019 IEEE international conference on image processing (ICIP). IEEE, 2019, pp. 1014–1018

    2019

  42. [42]

    Nh-haze: An image dehazing benchmark with non-homogeneous hazy and haze-free images,

    C. O. Ancuti, C. Ancuti, and R. Timofte, “Nh-haze: An image dehazing benchmark with non-homogeneous hazy and haze-free images,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, 2020, pp. 444–445

    2020

  43. [43]

    Sparse gradient regularized deep retinex network for robust low-light image enhance- ment,

    W. Yang, W. Wang, H. Huang, S. Wang, and J. Liu, “Sparse gradient regularized deep retinex network for robust low-light image enhance- ment,”IEEE Transactions on Image Processing, vol. 30, pp. 2072– 2086, 2021

    2072

  44. [44]

    Rethinking nighttime image deraining via learnable color space transformation,

    Q. Guan, X. Chen, G. Jin, J. Jin, S. Fan, T. Song, and J. Pan, “Rethinking nighttime image deraining via learnable color space transformation,”Advances in Neural Information Processing Systems, vol. 38, pp. 3189–3225, 2026

    2026

  45. [45]

    Lednet: Joint low-light enhance- ment and deblurring in the dark,

    S. Zhou, C. Li, and C. Change Loy, “Lednet: Joint low-light enhance- ment and deblurring in the dark,” inEuropean conference on computer vision. Springer, 2022, pp. 573–589

    2022

  46. [46]

    Onerestore: A universal restoration framework for composite degradation,

    Y . Guo, Y . Gao, Y . Lu, H. Zhu, R. W. Liu, and S. He, “Onerestore: A universal restoration framework for composite degradation,” in European conference on computer vision. Springer, 2024, pp. 255– 272

    2024

  47. [47]

    Endouic: Promptable diffusion transformer for unified illumination correction in capsule endoscopy,

    L. Bai, T. Chen, Q. Tan, W. J. Nah, Y . Li, Z. He, S. Yuan, Z. Chen, J. Wu, M. Islamet al., “Endouic: Promptable diffusion transformer for unified illumination correction in capsule endoscopy,” inInternational Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2024, pp. 296–306

    2024

  48. [48]

    Single satellite optical imagery dehazing using sar image prior based on conditional generative adversarial networks,

    B. Huang, L. Zhi, C. Yang, F. Sun, and Y . Song, “Single satellite optical imagery dehazing using sar image prior based on conditional generative adversarial networks,” inProceedings of the IEEE/CVF winter conference on applications of computer vision, 2020, pp. 1806– 1813

    2020

  49. [49]

    Cloud removal advances: A comprehensive review and analysis for optical remote sensing images,

    J. Ning, L. Xie, J. Yin, and Y . Liu, “Cloud removal advances: A comprehensive review and analysis for optical remote sensing images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025

    2025

  50. [50]

    Focal network for image restoration,

    Y . Cui, W. Ren, X. Cao, and A. Knoll, “Focal network for image restoration,” inProceedings of the IEEE/CVF international conference on computer vision, 2023, pp. 13 001–13 011

    2023

  51. [51]

    Swinir: Image restoration using swin transformer,

    J. Liang, J. Cao, G. Sun, K. Zhang, L. Van Gool, and R. Timofte, “Swinir: Image restoration using swin transformer,” inProceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 1833–1844

    2021

  52. [52]

    Simple baselines for image restoration,

    L. Chen, X. Chu, X. Zhang, and J. Sun, “Simple baselines for image restoration,” inProc. Eur. Conf. Comput. Vis. (ECCV), 2022, pp. 17–33

    2022

  53. [53]

    Restore anything with masks: Leveraging mask image modeling for blind all-in-one image restoration,

    C.-J. Qin, R.-Q. Wu, Z. Liu, X. Lin, C.-L. Guo, H. H. Park, and C. Li, “Restore anything with masks: Leveraging mask image modeling for blind all-in-one image restoration,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 364–380

    2024

  54. [54]

    Selective hourglass mapping for universal image restoration based on diffusion model,

    D. Zheng, X.-M. Wu, S. Yang, J. Zhang, J.-F. Hu, and W.-S. Zheng, “Selective hourglass mapping for universal image restoration based on diffusion model,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2024, pp. 25 445–25 455

    2024

  55. [55]

    Universal image restora- tion pre-training via degradation classification,

    J. Hu, L. Jin, Z. Yao, and Y . Lu, “Universal image restora- tion pre-training via degradation classification,”arXiv preprint arXiv:2501.15510, 2025

    work page arXiv 2025

  56. [56]

    Degradation-aware fea- ture perturbation for all-in-one image restoration,

    X. Tian, X. Liao, X. Liu, M. Li, and C. Ren, “Degradation-aware fea- ture perturbation for all-in-one image restoration,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025, pp. 28 165–28 175

    2025

  57. [57]

    Degradation-aware residual- conditioned optimal transport for unified image restoration,

    X. Tang, X. Gu, X. He, X. Hu, and J. Sun, “Degradation-aware residual- conditioned optimal transport for unified image restoration,”IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

    2025

  58. [58]

    Cycle-dehaze: Enhanced cyclegan for single image dehazing,

    D. Engin, A. Genc ¸, and H. Kemal Ekenel, “Cycle-dehaze: Enhanced cyclegan for single image dehazing,” inProceedings of the IEEE conference on computer vision and pattern recognition workshops, 2018, pp. 825–833

    2018

  59. [59]

    Transweather: Transformer-based restoration of images degraded by adverse weather conditions,

    J. M. J. Valanarasu, R. Yasarla, and V . M. Patel, “Transweather: Transformer-based restoration of images degraded by adverse weather conditions,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 2353–2363

    2022

  60. [60]

    Msp-former: Multi-scale projection transformer for single image desnowing,

    S. Chen, T. Ye, Y . Liu, T. Liao, J. Jiang, E. Chen, and P. Chen, “Msp-former: Multi-scale projection transformer for single image desnowing,” inICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023, pp. 1–5

    2023

  61. [61]

    Mb- taylorformer: Multi-branch efficient transformer expanded by taylor formula for image dehazing,

    Y . Qiu, K. Zhang, C. Wang, W. Luo, H. Li, and Z. Jin, “Mb- taylorformer: Multi-branch efficient transformer expanded by taylor formula for image dehazing,” inProceedings of the IEEE/CVF inter- national conference on computer vision, 2023, pp. 12 802–12 813

    2023

  62. [62]

    Irnext: Rethinking convolutional network design for image restoration,

    Y . Cui, W. Ren, S. Yang, X. Cao, and A. Knoll, “Irnext: Rethinking convolutional network design for image restoration,” 2023

    2023

  63. [63]

    Deep unfolding network for image desnowing with snow shape prior,

    X. Guo, X. Wang, X. Fu, and Z.-J. Zha, “Deep unfolding network for image desnowing with snow shape prior,”IEEE Transactions on Circuits and Systems for Video Technology, vol. 35, no. 5, pp. 4740– 4752, 2025

    2025

  64. [64]

    Uformer: A general u-shaped transformer for image restoration,

    Z. Wang, X. Cun, J. Bao, W. Zhou, J. Liu, and H. Li, “Uformer: A general u-shaped transformer for image restoration,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 17 683–17 693

    2022

  65. [65]

    Autodir: Automatic all-in-one image restoration with latent diffusion,

    Y . Jiang, Z. Zhang, T. Xue, and J. Gu, “Autodir: Automatic all-in-one image restoration with latent diffusion,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 340–359

    2024

  66. [66]

    A comparative study of image restoration networks for general back- bone network design,

    X. Chen, Z. Li, Y . Pu, Y . Liu, J. Zhou, Y . Qiao, and C. Dong, “A comparative study of image restoration networks for general back- bone network design,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 74–91

    2024

  67. [67]

    Foundir: Unleashing million-scale training data to advance foundation models for image restoration,

    H. Li, X. Chen, J. Dong, J. Tang, and J. Pan, “Foundir: Unleashing million-scale training data to advance foundation models for image restoration,” inProceedings of the IEEE/CVF international conference on computer vision, 2025, pp. 12 626–12 636

    2025

  68. [68]

    An intelligent agentic system for complex image restoration problems,

    K. Zhu, J. Gu, Z. You, Y . Qiao, and C. Dong, “An intelligent agentic system for complex image restoration problems,” inInternational Conference on Learning Representations, vol. 2025, 2025, pp. 57 985– 58 013

    2025

  69. [69]

    Foundir-v2: Optimizing pre-training data mixtures for image restoration foundation model,

    X. Chen, J. Pan, J. Dong, J. Yang, and J. Tang, “Foundir-v2: Optimizing pre-training data mixtures for image restoration foundation model,” arXiv preprint arXiv:2512.09282, 2025

    work page arXiv 2025

  70. [70]

    From fidelity to perceptual quality: A semi-supervised approach for low-light image en- hancement,

    W. Yang, S. Wang, Y . Fang, Y . Wang, and J. Liu, “From fidelity to perceptual quality: A semi-supervised approach for low-light image en- hancement,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 3063–3072

    2020

  71. [71]

    Learning enriched features for real image restoration and enhancement,

    S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, M.-H. Yang, and L. Shao, “Learning enriched features for real image restoration and enhancement,” inProc. Eur. Conf. Comput. Vis. (ECCV), 2020, pp. 492–511

    2020

  72. [72]

    Uretinex- net: Retinex-based deep unfolding network for low-light image en- hancement,

    W. Wu, J. Weng, P. Zhang, X. Wang, W. Yang, and J. Jiang, “Uretinex- net: Retinex-based deep unfolding network for low-light image en- hancement,” inProc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2022, pp. 5901–5910

    2022

  73. [73]

    Restormer: Efficient transformer for high-resolution image JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 13 restoration,

    S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, and M.- H. Yang, “Restormer: Efficient transformer for high-resolution image JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 13 restoration,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 5728–5739

    2021

  74. [74]

    Retinex- former: One-stage retinex-based transformer for low-light image en- hancement,

    Y . Cai, H. Bian, J. Lin, H. Wang, R. Timofte, and Y . Zhang, “Retinex- former: One-stage retinex-based transformer for low-light image en- hancement,” inProc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2023, pp. 12 504–12 513

    2023

  75. [75]

    Diffir: Efficient diffusion model for image restoration,

    B. Xia, Y . Zhang, S. Wang, Y . Wang, X. Wu, Y . Tian, W. Yang, and L. Van Gool, “Diffir: Efficient diffusion model for image restoration,” inProc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2023, pp. 13 095– 13 105

    2023

  76. [76]

    Fourllie: Boosting low-light image enhancement by fourier frequency information,

    C. Wang, H. Wu, and Z. Jin, “Fourllie: Boosting low-light image enhancement by fourier frequency information,” inProceedings of the 31st ACM international conference on multimedia, 2023, pp. 7459– 7469

    2023

  77. [77]

    Fourier priors-guided diffusion for zero-shot joint low-light enhance- ment and deblurring,

    X. Lv, S. Zhang, C. Wang, Y . Zheng, B. Zhong, C. Li, and L. Nie, “Fourier priors-guided diffusion for zero-shot joint low-light enhance- ment and deblurring,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2024, pp. 25 378–25 388

    2024

  78. [78]

    Adapt or perish: Adaptive sparse transformer with attentive feature refinement for image restoration,

    S. Zhou, D. Chen, J. Pan, J. Shi, and J. Yang, “Adapt or perish: Adaptive sparse transformer with attentive feature refinement for image restoration,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2024, pp. 2952–2963

    2024

  79. [79]

    Inter- pretable optimization-inspired unfolding network for low-light image enhancement,

    W. Wu, J. Weng, P. Zhang, X. Wang, W. Yang, and J. Jiang, “Inter- pretable optimization-inspired unfolding network for low-light image enhancement,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 4, pp. 2545–2562, 2025

    2025

  80. [80]

    Progressive image deraining networks: A better and simpler baseline,

    D. Ren, W. Zuo, Q. Hu, P. Zhu, and D. Meng, “Progressive image deraining networks: A better and simpler baseline,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 3937–3946

    2019

Showing first 80 references.