mlsanityData to 7 Oct 2026

OneRestore: A Universal Restoration Framework for Composite Degradation

arXiv 2407.04621 ↗First posted 5 Jul 2024cs.CVcited by 91

Not on the map. Why?

Abstract (arXiv)

In real-world scenarios, image impairments often manifest as composite degradations, presenting a complex interplay of elements such as low light, haze, rain, and snow. Despite this reality, existing restoration methods typically target isolated degradation types, thereby falling short in environments where multiple degrading factors coexist. To bridge this gap, our study proposes a versatile imaging model that consolidates four physical corruption paradigms to accurately represent complex, composite degradation scenarios. In this context, we propose OneRestore, a novel transformer-based framework designed for adaptive, controllable scene restoration. The proposed framework leverages a unique cross-attention mechanism, merging degraded scene descriptors with image features, allowing for nuanced restoration. Our model allows versatile input scene descriptors, ranging from manual text embeddings to automatic extractions based on visual attributes. Our methodology is further enhanced through a composite degradation restoration loss, using extra degraded images as negative samples to fortify model constraints. Comparative results on synthetic and real-world datasets demonstrate OneRestore as a superior solution, significantly advancing the state-of-the-art in addressing complex, composite degradations.

Key facts. Cited by 91 papers in the map (data through 7 Oct 2026). Builds on 53 of its 101 references that are in the map. First posted on arXiv 5 Jul 2024.

Builds on

53 of 101 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  3. 2015Fast R-CNNcited by 2,930
  4. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  5. 2020Pre-Trained Image Processing Transformercited by 891
  6. 2021Multi-Stage Progressive Image Restorationcited by 813
  7. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  8. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 720
  9. 2022Simple Baselines for Image Restorationcited by 701
  10. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 541
  11. 2017Benchmarking Single Image Dehazing and Beyondcited by 445
  12. 2019Kindling the Darkness: A Practical Low-light Image Enhancercited by 355
38 more
  1. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 351
  2. 2016DehazeNet: An End-to-End System for Single Image Haze Removalcited by 313
  3. 2020Learning Enriched Features for Real Image Restoration and Enhancementcited by 311
  4. 2019FFA-Net: Feature Fusion Attention Network for Single Image Dehazingcited by 307
  5. 2020Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancementcited by 303
  6. 2019Progressive Image Deraining Networks: A Better and Simpler Baselinecited by 271
  7. 2022Vision Transformers for Single Image Dehazingcited by 255
  8. 2018Density-aware Single Image De-raining using a Multi-stream Dense Networkcited by 248
  9. 2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 243
  10. 2020Multi-Scale Boosted Dehazing Network with Dense Feature Fusioncited by 229
  11. 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 228
  12. 2019GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazingcited by 227
  13. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
  14. 2022Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Modelscited by 215
  15. 2018Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Derainingcited by 205
  16. 2023Learning A Sparse Transformer Network for Effective Image Derainingcited by 204
  17. 2017DesnowNet: Context-Aware Deep Network for Snow Removalcited by 200
  18. 2019Spatial Attentive Single-Image Deraining with a High Quality Real Rain Datasetcited by 192
  19. 2021Low-Light Image Enhancement with Normalizing Flowcited by 184
  20. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  21. 2019Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learningcited by 157
  22. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  23. 2016Clearing the Skies: A deep network architecture for single-image rain removalcited by 136
  24. 2022Deep Generalized Unfolding Networks for Image Restorationcited by 119
  25. 2019Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Rainingcited by 117
  26. 2015Attribute2Image: Conditional Image Generation from Visual Attributescited by 93
  27. 2018Gated Context Aggregation Network for Image Dehazing and Derainingcited by 89
  28. 2023Curricular Contrastive Regularization for Physics-aware Single Image Dehazingcited by 83
  29. 2021Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priorscited by 82
  30. 2023MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazingcited by 81
  31. 2023Low-Light Image Enhancement via Structure Modeling and Guidancecited by 78
  32. 2021Low-light Image Enhancement via Breaking Down the Darknesscited by 65
  33. 2021Structure-Preserving Deraining with Residue Channel Prior Guidancecited by 63
  34. 2022Disentangling Visual Embeddings for Attributes and Objectscited by 55
  35. 2022MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowingcited by 39
  36. 2023Learning Conditional Attributes for Compositional Zero-Shot Learningcited by 28
  37. 2022DRT: A Lightweight Single Image Deraining Recursive Transformercited by 26
  38. 2021Blind Image Decompositioncited by 18

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 41; 2026: 42.

91 papers.

Sort:

By area:

  1. 2024Complexity Experts are Task-Discriminative Learners for Any Image Restorationcited by 72
  2. 2024A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trendscited by 58
  3. 2024FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restorationcited by 37
  4. 2025Visual-Instructed Degradation Diffusion for All-in-One Image Restorationcited by 26
  5. 2025RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restorationcited by 15
  6. 2025Hybrid Agents for Image Restorationcited by 14
  7. 2025Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Visioncited by 14
  8. 2026Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restorationcited by 14
  9. 2024UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularitycited by 12
  10. 2026ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restorationcited by 11
  11. 2025CWNet: Causal Wavelet Network for Low-Light Image Enhancementcited by 10
  12. 2026RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Modelscited by 9
38 more
  1. 2025ControlFusion: A Controllable Image Fusion Framework with Language-Vision Degradation Promptscited by 8
  2. 2025Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularizationcited by 8
  3. 2025When Schr"odinger Bridge Meets Real-World Image Dehazing with Unpaired Trainingcited by 8
  4. 2026CLIP-Guided Data Augmentation for Night-Time Image Dehazingcited by 8
  5. 2025DSwinIR: Rethinking Window-based Attention for Image Restorationcited by 7
  6. 2025EvoIR: Towards All-in-One Image Restoration via Evolutionary Frequency Modulationcited by 7
  7. 2024PromptHSI: Universal Hyperspectral Image Restoration with Vision-Language Modulated Frequency Adaptationcited by 6
  8. 2025MP-HSIR: A Multi-Prompt Framework for Universal Hyperspectral Image Restorationcited by 6
  9. 2025Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restorationcited by 6
  10. 2025M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restorationcited by 6
  11. 2024AllRestorer: All-in-One Transformer for Image Restoration under Composite Degradationscited by 5
  12. 2025Enhancing Image Restoration Transformer via Adaptive Translation Equivariancecited by 5
  13. 2025UltraFast-LiNET: Light-weight multi-scale shift convolutional network for real-time low-light image enhancementcited by 5
  14. 2025UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancementcited by 5
  15. 2024Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorerscited by 4
  16. 2025Learning Where and What to Restore for Composite Image Restorationcited by 4
  17. 2025An Efficient and Mixed Heterogeneous Model for Image Restorationcited by 4
  18. 2025Universal Image Restoration Pre-training via Masked Degradation Classificationcited by 4
  19. 2025Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidancecited by 4
  20. 2025ClusIR: Towards Cluster-Guided All-in-One Image Restorationcited by 4
  21. 2026Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translationcited by 4
  22. 2024Adaptive Blind All-in-One Image Restorationcited by 3
  23. 2025DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Modelcited by 3
  24. 2025Instruct2See: Learning to Remove Any Obstructions Across Distributionscited by 3
  25. 2025UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restorationcited by 3
  26. 2025FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restorationcited by 3
  27. 2026TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restorationcited by 3
  28. 2025VL-UR: Vision-Language-guided Universal Restoration of Images Degraded by Adverse Weather Conditionscited by 2
  29. 2025Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restorationcited by 2
  30. 2025Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Startcited by 2
  31. 2025Test-Time Preference Optimization for Image Restorationcited by 2
  32. 2026PaAgent: Portrait-Aware Image Restoration Agent via Subjective-Objective Reinforcement Learningcited by 2
  33. 2026NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weathercited by 2
  34. 2026SpikeRestormer: Towards Energy-Efficient All-in-One Image Restoration via Unified Event Reasoningcited by 2
  35. 2025Any Image Restoration via Efficient Spatial-Frequency Degradation Adaptationcited by 1
  36. 2025Boosting All-in-One Image Restoration via Self-Improved Privilege Learningcited by 1
  37. 2025RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restorationcited by 1
  38. 2025Degradation-Aware All-in-One Image Restoration via Latent Prior Encodingcited by 1

50 most cited of 91 All 91 (JSON)