Di$^2$CycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schrödinger Bridge Transformer
Computer Vision and Pattern Recognition
Summary
The authors address the problem of bright light effects reducing visibility in nighttime images. They create a new method called Di²CycleSB that uses a type of AI model called a Transformer combined with special image priors to estimate and remove these light effects. Unlike earlier methods, their approach does not rely on preset assumptions or complicated image splitting. Their experiments show this method improves nighttime images effectively and works without regularization or decomposition steps.
Authors
Hanting Li, Xin Sun, Wei Ye, Jungong Han, Liang-jie Zhang
Abstract
Light-effect contamination poses a significant challenge to nighttime visibility enhancement. Most methods suppress light effects by estimating and decomposing them through prior-driven regularization, yet they are often limited by hand-crafted priors and ill-posed nature of decomposition. This work proposes Di$^2$CycleSB, a unsupervised Cycle Schrödinger Bridge Transformer framework guided by dynamic integral image priors, for high-quality unsupervised nighttime visibility enhancement. Specifically, a novel light-effect estimator is introduced to parameterize Gaussian-like adaptive priors by aggregating dynamic integral image representations for non-uniform glow estimation. Then, we propose a prior-informed Generator that exploits light-effect representations to guide long-range dependency modeling within our specific Transformer blocks. We formulate light-effect suppression as a Schrödinger bridge problem and construct forward and backward bridges with cycle consistency constraints to achieve visually pleasing enhancement. Extensive experiments on real-world datasets demonstrate the remarkable effectiveness of our Di$^2$CycleSB in enhancing nighttime visibility. In particular, it achieves effective end-to-end light-effect suppression without any regularization constraints and image decomposition. The code and models are available at https://github.com/LHTcode/Di2CycleSB.