DenseSR: Image Shadow Removal as Dense Prediction

TL;DR

DenseSR introduces a dense prediction framework for single-image shadow removal that combines scene understanding with high-fidelity restoration, effectively addressing issues of inconsistency and blurring in shadowed images.

Contribution

The paper proposes DenseSR, a novel dense prediction approach with a Dense Fusion Block and geometric-semantic priors for improved shadow removal quality.

Findings

Outperforms existing shadow removal methods in quality.

Effectively preserves textures and sharp boundaries.

Demonstrates robustness under challenging lighting conditions.

Abstract

Shadows are a common factor degrading image quality. Single-image shadow removal (SR), particularly under challenging indirect illumination, is hampered by non-uniform content degradation and inherent ambiguity. Consequently, traditional methods often fail to simultaneously recover intra-shadow details and maintain sharp boundaries, resulting in inconsistent restoration and blurring that negatively affect both downstream applications and the overall viewing experience. To overcome these limitations, we propose the DenseSR, approaching the problem from a dense prediction perspective to emphasize restoration quality. This framework uniquely synergizes two key strategies: (1) deep scene understanding guided by geometric-semantic priors to resolve ambiguity and implicitly localize shadows, and (2) high-fidelity restoration via a novel Dense Fusion Block (DFB) in the decoder. The DFB employs adaptive component processing-using an Adaptive Content Smoothing Module (ACSM) for consistent appearance and a Texture-Boundary Recuperation Module (TBRM) for fine textures and sharp boundaries-thereby directly tackling the inconsistent restoration and blurring issues. These purposefully processed components are effectively fused, yielding an optimized feature representation preserving both consistency and fidelity. Extensive experimental results demonstrate the merits of our approach over existing methods. Our code can be available on https://github$.$com/VanLinLin/DenseSR