Fine-Context Shadow Detection using Shadow Removal

TL;DR

This paper introduces a novel shadow detection network that leverages shadow removal features and fine context learning to improve detection accuracy, especially for small or blurry shadows.

Contribution

The paper proposes FCSD-Net with a new R2D training strategy and a CFL block, enhancing shadow detection by integrating shadow removal features and focusing on fine context.

Findings

Improved shadow detection accuracy on ISTD, SBU, and UCF datasets.

Better detection of small, unclear, or blurry shadow regions.

Outperforms recent methods in shadow detection benchmarks.

Abstract

Current shadow detection methods perform poorly when detecting shadow regions that are small, unclear or have blurry edges. In this work, we attempt to address this problem on two fronts. First, 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. Second, we propose a new learning strategy, 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. We train the proposed network, FCSD-Net, using the R2D learning strategy across multiple datasets. Experimental results on three public shadow detection datasets (ISTD, SBU and UCF) show that our method improves the shadow detection performance while being able to detect fine context better compared to the other recent methods.