paper-with-me

홈 › Papers

Rethinking Generative Methods for Image Restoration in Physics-based Vision: A Theoretical Analysis from the Perspective of Information

2022-12-05 · Xudong Kang, Haoran Xie, Man-Leung Wong, Jing Qin

End-to-end generative methods are considered a more promising solution for image restoration in physics-based vision compared with the traditional deconstructive methods based on handcrafted composition models. However, existing generative methods still have plenty of room for improvement in quantitative performance. More crucially, these methods are considered black boxes due to weak interpretability and there is rarely a theory trying to explain their mechanism and learning process. In this study, we try to re-interpret these generative methods for image restoration tasks using information theory. Different from conventional understanding, we analyzed the information flow of these methods and identified three sources of information (extracted high-level information, retained low-level information, and external information that is absent from the source inputs) are involved and optimized respectively in generating the restoration results. We further derived their learning behaviors, optimization objectives, and the corresponding information boundaries by extending the information bottleneck principle. Based on this theoretic framework, we found that many existing generative methods tend to be direct applications of the general models designed for conventional generation tasks, which may suffer from problems including over-invested abstraction processes, inherent details loss, and vanishing gradients or imbalance in training. We analyzed these issues with both intuitive and theoretical explanations and proved them with empirical evidence respectively. Ultimately, we proposed general solutions or ideas to address the above issue and validated these approaches with performance boosts on six datasets of three different image restoration tasks.

📄 PDF Abstract BibTeX arXiv:2212.02198

Code (0)

등록된 구현이 없습니다.

Tasks

Image Restoration

Similar Papers 제목 키워드 기반

Physics-Based Generative Adversarial Models for Image Restoration and Beyond

2018-08-02 · Jinshan Pan, Jiangxin Dong, Yang Liu, Jiawei Zhang 외

We present an algorithm to directly solve numerous image restoration problems (e.g., image deblurring, image dehazing, image deraining, etc.). These problems are highly ill-posed, and the common assumptions for existing …

DeblurringImage DeblurringImage DehazingImage Restoration+1

HDRFace: Rethinking Face Restoration with High-Dimensional Representation

2026-05-14 · Zirui Wang, Xianhui Lin, Yi Dong, Bo Wei 외 arxiv

Face restoration under complex degradations still remains an ill-posed inverse problem due to severe information loss. Although diffusion models benefit from strong generative priors, most methods still condition only on…

HSI-VAR: Rethinking Hyperspectral Restoration through Spatial-Spectral Visual Autoregression

2026-01-31 · Xiangming Wang, Benteng Sun, Yungeng Liu, Haijin Zeng 외 arxiv

Hyperspectral images (HSIs) capture richer spatial-spectral information beyond RGB, yet real-world HSIs often suffer from a composite mix of degradations, such as noise, blur, and missing bands. Existing generative appro…

Rethinking Image Restoration for Object Detection

2022-11-01 · NIPS 2022 11 · Shangquan Sun, Wenqi Ren, Tao Wang, Xiaochun Cao

Although image restoration has achieved significant progress, its potential to assist object detectors in adverse imaging conditions lacks enough attention. It is reported that the existing image restoration methods cann…

Adversarial AttackDomain AdaptationImage DehazingImage Restoration+3

LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models

2026-06-01 · Lu Liu, Huiyu Duan, Chenxin Zhu, Jintong Lu 외 arxiv

Large-scale generative models have demonstrated remarkable capabilities across image generation and editing tasks. However, their performance in low-level vision tasks, which require pixel-wise control, remains insuffici…

Image Quality AssessmentImage Generation