# Di2CycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schr"odinger Bridge Transformer

arXiv: https://arxiv.org/abs/2608.29043 · HTML: https://mlsanity.com/paper/2608.29043/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 58 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Builds on (most cited first, 30 of 42)

- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modeling](https://mlsanity.com/paper/2106.01357/) (2021)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [A survey of the Schr"odinger problem and some of its connections with optimal transport](https://mlsanity.com/paper/1308.0215/) (2013)
- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [StyTr2: Image Style Transfer with Transformers](https://mlsanity.com/paper/2105.14576/) (2021)
- [Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method](https://mlsanity.com/paper/2212.11548/) (2022)
- [Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration](https://mlsanity.com/paper/2303.11435/) (2023)
- [Unpaired Image-to-Image Translation via Neural Schr"odinger Bridge](https://mlsanity.com/paper/2305.15086/) (2023)
- [Diffusion Models in Low-Level Vision: A Survey](https://mlsanity.com/paper/2406.11138/) (2024)
- [Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression](https://mlsanity.com/paper/2207.10564/) (2022)
- [CycleGAN, a Master of Steganography](https://mlsanity.com/paper/1712.02950/) (2017)
- [ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models](https://mlsanity.com/paper/2502.09696/) (2025)
- [Entropic Neural Optimal Transport via Diffusion Processes](https://mlsanity.com/paper/2211.01156/) (2022)
- [Flare7K: A Phenomenological Nighttime Flare Removal Dataset](https://mlsanity.com/paper/2210.06570/) (2022)
- [Wave-Mamba: Wavelet State Space Model for Ultra-High-Definition Low-Light Image Enhancement](https://mlsanity.com/paper/2408.01276/) (2024)
- [Schr"odinger Bridge Flow for Unpaired Data Translation](https://mlsanity.com/paper/2409.09347/) (2024)
- [Nighttime Dehazing with a Synthetic Benchmark](https://mlsanity.com/paper/2008.03864/) (2020)
- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [Style Transformer for Image Inversion and Editing](https://mlsanity.com/paper/2203.07932/) (2022)
- [Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond](https://mlsanity.com/paper/2306.04236/) (2023)
- [Learning to Rank for Blind Image Quality Assessment](https://mlsanity.com/paper/1309.0213/) (2013)

## Abstract (arXiv)

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 Di2CycleSB, a unsupervised Cycle Schr"odinger 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 Schr"odinger 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 Di2CycleSB 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.