mlsanityData to 14 Oct 2026

A Preliminary Exploration Towards General Image Restoration

arXiv 2408.15143 ↗First posted 27 Aug 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Despite the tremendous success of deep models in various individual image restoration tasks, there are at least two major technical challenges preventing these works from being applied to real-world usages: (1) the lack of generalization ability and (2) the complex and unknown degradations in real-world scenarios. Existing deep models, tailored for specific individual image restoration tasks, often fall short in effectively addressing these challenges. In this paper, we present a new problem called general image restoration (GIR) which aims to address these challenges within a unified model. GIR covers most individual image restoration tasks (eg, image denoising, deblurring, deraining and super-resolution) and their combinations for general purposes. This paper proceeds to delineate the essential aspects of GIR, including problem definition and the overarching significance of generalization performance. Moreover, the establishment of new datasets and a thorough evaluation framework for GIR models is discussed. We conduct a comprehensive evaluation of existing approaches for tackling the GIR challenge, illuminating their strengths and pragmatic challenges. By analyzing these approaches, we not only underscore the effectiveness of GIR but also highlight the difficulties in its practical implementation. At last, we also try to understand and interpret these models' behaviors to inspire the future direction. Our work can open up new valuable research directions and contribute to the research of general vision.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 92 of its 125 references that are in the map. First posted on arXiv 27 Aug 2024.

Builds on

92 of 125 references.

References · 92

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  7. 2023GPT-4 Technical Reportcited by 18,396
  8. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  9. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  10. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  11. 2023Visual Instruction Tuningcited by 7,869
  12. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
38 more
  1. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  2. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  3. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  4. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  5. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  6. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  7. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  8. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  9. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  10. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  11. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  12. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  13. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  14. 2021Scaling Vision Transformerscited by 999
  15. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  16. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
  17. 2020Pre-Trained Image Processing Transformercited by 893
  18. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 866
  19. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
  20. 2021Multi-Stage Progressive Image Restorationcited by 816
  21. 2021Scaling Vision with Sparse Mixture of Expertscited by 747
  22. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 727
  23. 2022Simple Baselines for Image Restorationcited by 708
  24. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 569
  25. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  26. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 510
  27. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  28. 2017Benchmarking Single Image Dehazing and Beyondcited by 447
  29. 2022Activating More Pixels in Image Super-Resolution Transformercited by 438
  30. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 403
  31. 2024InternLM2 Technical Reportcited by 397
  32. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 367
  33. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 352
  34. 2018Scale-recurrent Network for Deep Image Deblurringcited by 333
  35. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 315
  36. 2016DehazeNet: An End-to-End System for Single Image Haze Removalcited by 314
  37. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 286
  38. 2019Progressive Image Deraining Networks: A Better and Simpler Baselinecited by 272

50 most cited of 92 All 92 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 1.

6 papers.

  1. 2024An Intelligent Agentic System for Complex Image Restoration Problemscited by 43
  2. 2024GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restorationcited by 13
  3. 2025Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedbackcited by 6
  4. 2025Exploring Scalable Unified Modeling for General Low-Level Visioncited by 4
  5. 2025Position: Agentic Systems Constitute a Key Component of Next-Generation Intelligent Image Processingcited by 3
  6. 2026GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restorationcited by 1