DTTNet: Improving Video Shadow Detection via Dark-Aware Guidance and Tokenized Temporal Modeling
This work improves video shadow detection for computer vision applications, but it is incremental as it builds on existing methods with specific enhancements.
The paper tackles video shadow detection by addressing shadow-background ambiguity and dynamic shadow deformations, achieving state-of-the-art accuracy and real-time inference efficiency on multiple benchmark datasets.
Video shadow detection confronts two entwined difficulties: distinguishing shadows from complex backgrounds and modeling dynamic shadow deformations under varying illumination. To address shadow-background ambiguity, we leverage linguistic priors through the proposed Vision-language Match Module (VMM) and a Dark-aware Semantic Block (DSB), extracting text-guided features to explicitly differentiate shadows from dark objects. Furthermore, we introduce adaptive mask reweighting to downweight penumbra regions during training and apply edge masks at the final decoder stage for better supervision. For temporal modeling of variable shadow shapes, we propose a Tokenized Temporal Block (TTB) that decouples spatiotemporal learning. TTB summarizes cross-frame shadow semantics into learnable temporal tokens, enabling efficient sequence encoding with minimal computation overhead. Comprehensive Experiments on multiple benchmark datasets demonstrate state-of-the-art accuracy and real-time inference efficiency. Codes are available at https://github.com/city-cheng/DTTNet.