Spatial-temporal Fusion Network for Fast Video Shadow Detection
Junhao Lin, Liansheng Wang · 2022
Existing video shadow detectors often need postprocessing or additional input to perform better, thereby degrading their video shadow detection speed. In this work, we present a novel spatial-temporal fusion network (STF-Net), which can efficiently detect shadows in videos with real-time speed (30FPS) and postprocessing-free. Our STF-Net is based solely on an attention-based spatial-temporal fusion block, equipping with recurrence and CNNs entirely. Experimental results on ViSha validation dataset show that our network exceeds state-of-the-art methods quantitatively and qualitatively.