Abstract:Adverse lighting conditions, such as cast shadows and irregular illumination, pose significant challenges to computer vision systems by degrading visibility and color fidelity. Consequently, effective shadow removal and ALN are critical for restoring underlying image content, improving perceptual quality, and facilitating robust performance in downstream tasks. However, while achieving state-of-the-art results on specific benchmarks is a primary goal in image restoration challenges, real-world applications often demand robust models capable of handling diverse domains. To address this, we present a comprehensive study on lighting-related image restoration by exploring two contrasting strategies. We leverage a robust framework for ALN, DINOLight, as a specialized baseline to exploit the characteristics of each individual dataset, and extend it to OmniLight, a generalized alternative incorporating our proposed Wavelet Domain Mixture-of-Experts (WD-MoE) that is trained across all provided datasets. Through a comparative analysis of these two methods, we discuss the impact of data distribution on the performance of specialized and unified architectures in lighting-related image restoration. Notably, both approaches secured top-tier rankings across all three lighting-related tracks in the NTIRE 2026 Challenge, demonstrating their outstanding perceptual quality and generalization capabilities. Our codes are available at this https URL.
| Comments: | CVPRW 2026; NTIRE 2026 Image Shadow Removal & Ambient Lighting Normalization Challenges (1st Perceptual Rank for White Lighting, 2nd Fidelity Rank & 4th Perceptual Rank for Color Lighting) |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2604.15170 [cs.CV] |
| (or arXiv:2604.15170v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2604.15170 arXiv-issued DOI via DataCite (pending registration) |
From: Youngjin Oh [view email]
[v1]
Thu, 16 Apr 2026 15:47:49 UTC (3,906 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。