Metraipolis › archive › dc_a94ae57bf882
Di$^2$CycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schrödinger Bridge Transformer — arXiv:2608.29043
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29043
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:53:28.187Z
- SHA-256 of the archived text
398e5a61b9883f636de7c97a773031e9312f0fc314356dff744d10f38381e241- Stable URL of this page
https://metraipolis.com/documento/dc_a94ae57bf882
How to cite
Di$^2$CycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schrödinger Bridge Transformer — arXiv:2608.29043 — arXiv (en), https://arxiv.org/abs/2608.29043 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a94ae57bf882 (Metraipolis archive dc_a94ae57bf882, sha256 398e5a61b9883f636de7c97a773031e9312f0fc314356dff744d10f38381e241)
BibTeX
@misc{dca94ae57bf882,
title = {Di$^2$CycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schrödinger Bridge Transformer — arXiv:2608.29043},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29043},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a94ae57bf882; sha256 398e5a61b9883f636de7c97a773031e9312f0fc314356dff744d10f38381e241},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29043. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.29043 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T09:28:47.973Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).