Di$^2$CycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schrödinger Bridge Transformer

2026-08-29

AI Summary

本文提出Di²CycleSB，通过动态积分图像先验引导的循环薛定谔桥变换器框架，解决夜间光照效果污染问题，实现高质量的无监督夜间可见度增强。

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.

Problem

• nighttime visibility enhancement
• light-effect contamination
• prior-driven regularization
• decomposition

Innovation

• Unsupervised Nighttime Visibility Enhancement
• Schrödinger Bridge Transformer
• Dynamic Integral Image Priors
• Light-effect Estimator
• Cycle Consistency Constraints