Can I read CERL: A Unified Optimization Framework for Light Enhancement with Realistic Noise on EtoBox?

CERL: A Unified Optimization Framework for Light Enhancement with Realistic Noise by Chen, Zeyuan; Jiang, Yifan; Liu, Dong; Wang, Zhangyang is a scholarly article available to read on EtoBox.

What is CERL: A Unified Optimization Framework for Light Enhancement with Realistic Noise about?

Low-light images captured in the real world are inevitably corrupted by sensor noise. Such noise is spatially variant and highly dependent on the underlying pixel intensity, deviating from the oversimplified assumptions in conventional denoising. Existing light enhancement methods either overlook the important impact of real-world noise during enhancement, or treat noise removal as a separate pre- or post-processing step. We present \underline{C}oordinated \underline{E}nhancement for \underline{R}eal-world \underline{L}ow-light Noisy Images (CERL), that seamlessly integrates light enhancement and noise suppression parts into a unified and physics-grounded optimization framework. For the real low-light noise removal part, we customize a self-supervised denoising model that can easily be adapted without referring to clean ground-truth images. For the light enhancement part, we also improve the design of a state-of-the-art backbone. The two parts are then joint formulated into one principled plug-and-play optimization. Our approach is compared against state-of-the-art low-light enhancement methods both qualitatively and quantitatively. Besides standard benchmarks, we further collect a

Author

Chen, Zeyuan; Jiang, Yifan; Liu, Dong; Wang, Zhangyang

Published

2021

Language

EN