Shadow-Aware Dynamic Convolution for Shadow Removal

TL;DR

This paper proposes a shadow-aware dynamic convolution module that decouples shadow and non-shadow regions, improving shadow removal quality and efficiency by processing these regions with different convolution strategies.

Contribution

Introduction of a novel plug-and-play Shadow-Aware Dynamic Convolution (SADC) module that separates shadow and non-shadow processing for better shadow removal.

Findings

Achieves superior performance on ISTD and SRD datasets.

Reduces computational cost compared to existing methods.

Enhances image reconstruction quality in shadow regions.

Abstract

With a wide range of shadows in many collected images, shadow removal has aroused increasing attention since uncontaminated images are of vital importance for many downstream multimedia tasks. Current methods consider the same convolution operations for both shadow and non-shadow regions while ignoring the large gap between the color mappings for the shadow region and the non-shadow region, leading to poor quality of reconstructed images and a heavy computation burden. To solve this problem, this paper introduces a novel plug-and-play Shadow-Aware Dynamic Convolution (SADC) module to decouple the interdependence between the shadow region and the non-shadow region. Inspired by the fact that the color mapping of the non-shadow region is easier to learn, our SADC processes the non-shadow region with a lightweight convolution module in a computationally cheap manner and recovers the shadow region with a more complicated convolution module to ensure the quality of image reconstruction. Given that the non-shadow region often contains more background color information, we further develop a novel intra-convolution distillation loss to strengthen the information flow from the non-shadow region to the shadow region. Extensive experiments on the ISTD and SRD datasets show our method achieves better performance in shadow removal over many state-of-the-arts. Our code is available at https://github.com/xuyimin0926/SADC.