Priors in Deep Image Restoration and Enhancement: A Survey
Not on the map. Why?
Abstract (arXiv)
Image restoration and enhancement is a process of improving the image quality by removing degradations, such as noise, blur, and resolution degradation. Deep learning (DL) has recently been applied to image restoration and enhancement. Due to its ill-posed property, plenty of works have been explored priors to facilitate training deep neural networks (DNNs). However, the importance of priors has not been systematically studied and analyzed by far in the research community. Therefore, this paper serves as the first study that provides a comprehensive overview of recent advancements in priors for deep image restoration and enhancement. Our work covers five primary contents: (1) A theoretical analysis of priors for deep image restoration and enhancement; (2) A hierarchical and structural taxonomy of priors commonly used in the DL-based methods; (3) An insightful discussion on each prior regarding its principle, potential, and applications; (4) A summary of crucial problems by highlighting the potential future directions, especially adopting the large-scale foundation models as prior, to spark more research in the community; (5) An open-source repository that provides a taxonomy of all mentioned works and code links.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 125 of its 231 references that are in the map. First posted on arXiv 4 Jun 2022.
Builds on
125 of 231 references.
References · 125
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
- 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
- 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
- 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
- 2017Non-local Neural Networkscited by 2,290
38 more
- 2021Learning to Prompt for Vision-Language Modelscited by 2,269
- 2020Shortcut Learning in Deep Neural Networkscited by 1,928
- 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
- 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
- 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
- 2017Deep Image Priorcited by 1,097
- 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
- 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
- 2021Transformers in Vision: A Surveycited by 1,009
- 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
- 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
- 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
- 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 720
- 2017Video Enhancement with Task-Oriented Flowcited by 612
- 2015Holistically-Nested Edge Detectioncited by 590
- 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
- 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
- 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 421
- 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
- 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
- 2019Deep Learning for Image Super-resolution: A Surveycited by 368
- 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
- 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
- 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
- 2019Kindling the Darkness: A Practical Low-light Image Enhancercited by 355
- 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 351
- 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
- 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 340
- 2017Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolationcited by 321
- 2016DehazeNet: An End-to-End System for Single Image Haze Removalcited by 313
- 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
- 2020StyleRig: Rigging StyleGAN for 3D Control over Portrait Imagescited by 267
- 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
- 2019Residual Non-local Attention Networks for Image Restorationcited by 236
- 2018TDAN: Temporally Deformable Alignment Network for Video Super-Resolutioncited by 225
- 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
- 2022VRT: A Video Restoration Transformercited by 219
- 2018Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Derainingcited by 205
50 most cited of 125 All 125 (JSON)
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 1.
3 papers.