SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global