Learning Physical-Spatio-Temporal Features for Video Shadow Removal

• Published in: IEEE transactions on circuits and systems for video technology 2024-07, Vol.34 (7), p.5830-5842
• Main Authors: Chen, Zhihao, Wan, Liang, Xiao, Yefan, Zhu, Lei, Fu, Huazhu
• Format: Article
• Language: English
• Subjects: Adaptation models; Circuits and systems; Datasets; Effectiveness; Feature extraction; Games; Illumination; Image restoration; Lighting; physical-spatio-temporal features; Root-mean-square errors; Shadows; Strategy; synthetic scenes; Task analysis; Video shadow removal
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2024.3369910

Shadow removal in a single image has received increasing attention in recent years. However, removing shadows over dynamic scenes remains largely under-explored. In this paper, we propose the first data-driven video shadow removal model, termed PSTNet, by exploiting three essential characteristics of video shadows, i.e., physical property, spatio relation, and temporal coherence. Specifically, a dedicated physical branch was established to conduct local illumination estimation, which is more applicable for scenes with complex lighting and textures, and then enhance the physical features via a mask-guided attention strategy. Then, we develop a progressive aggregation module to enhance the spatio and temporal characteristics of features maps, and effectively integrate the three kinds of features. Furthermore, to tackle the lack of datasets of paired shadow videos, we synthesize a dataset (SVSRD-85) with aid of the popular game GTAV by controlling the switch of the shadow renderer. Experiments against 9 state-of-the-art models, including image shadow removers and image/video restoration methods, show that our method improves the best SOTA in terms of RMSE error for the shadow area by 14.7%. In addition, we develop a lightweight model adaptation strategy to make our synthetic-driven model effective in real world scenes. The visual comparison on the public SBU-TimeLapse dataset verifies the generalization ability of our model in real scenes.