R2D: Learning Shadow Removal to Enhance Fine-Context Shadow Detection
share
Current shadow detection methods perform poorly when detecting shadow regions that are small, unclear or have blurry edges. To tackle this problem, we propose a new method called Restore to Detect (R2D), where we show that when a deep neural network is trained for restoration (shadow removal), it learns meaningful features to delineate the shadow masks as well. To make use of this complementary nature of shadow detection and removal tasks, we train an auxiliary network for shadow removal and propose a complementary feature learning block (CFL) to learn and fuse meaningful features from shadow removal network to the shadow detection network. For the detection network in R2D, we propose a Fine Context-aware Shadow Detection Network (FCSD-Net) where we constraint the receptive field size and focus on low-level features to learn fine context features better. Experimental results on three public shadow detection datasets (ISTD, SBU and UCF) show that our proposed method R2D improves the shadow detection performance while being able to detect fine context better compared to the other recent methods.
READ FULL TEXT