Learning to Adapt to Light
Kai-Fu Yang, Cheng Cheng, Shi-Xuan Zhao, Xian-Shi Zhang, Yong-Jie Li

TL;DR
This paper introduces LA-Net, a unified, biologically inspired neural network that effectively handles various light-related image enhancement tasks by decomposing images into frequency components and adapting to light conditions.
Contribution
The study proposes a novel unified model inspired by biological visual adaptation, capable of addressing multiple light-related image enhancement tasks simultaneously.
Findings
Achieves near state-of-the-art results on low-light enhancement, exposure correction, and tone mapping.
Effectively separates common and task-specific features through frequency-based decomposition.
Demonstrates the effectiveness of biologically inspired adaptation mechanisms in image processing.
Abstract
Light adaptation or brightness correction is a key step in improving the contrast and visual appeal of an image. There are multiple light-related tasks (for example, low-light enhancement and exposure correction) and previous studies have mainly investigated these tasks individually. However, it is interesting to consider whether these light-related tasks can be executed by a unified model, especially considering that our visual system adapts to external light in such way. In this study, we propose a biologically inspired method to handle light-related image-enhancement tasks with a unified network (called LA-Net). First, a frequency-based decomposition module is designed to decouple the common and characteristic sub-problems of light-related tasks into two pathways. Then, a new module is built inspired by biological visual adaptation to achieve unified light adaptation in the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
