ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformer

TL;DR

ShadowRefiner introduces a mask-free shadow removal method using a Fast Fourier Transformer to effectively eliminate shadows while preserving details, achieving top performance in NTIRE 2024 challenge.

Contribution

We propose a novel mask-free shadow removal network with a Fast Fourier Transformer and a new attention mechanism for improved shadow elimination and image quality.

Findings

Wins first place in NTIRE 2024 Perceptual Track.

Achieves second place in NTIRE 2024 Fidelity Track.

Demonstrates superior effectiveness through extensive experiments.

Abstract

Shadow-affected images often exhibit pronounced spatial discrepancies in color and illumination, consequently degrading various vision applications including object detection and segmentation systems. To effectively eliminate shadows in real-world images while preserving intricate details and producing visually compelling outcomes, we introduce a mask-free Shadow Removal and Refinement network (ShadowRefiner) via Fast Fourier Transformer. Specifically, the Shadow Removal module in our method aims to establish effective mappings between shadow-affected and shadow-free images via spatial and frequency representation learning. To mitigate the pixel misalignment and further improve the image quality, we propose a novel Fast-Fourier Attention based Transformer (FFAT) architecture, where an innovative attention mechanism is designed for meticulous refinement. Our method wins the championship in the Perceptual Track and achieves the second best performance in the Fidelity Track of NTIRE 2024 Image Shadow Removal Challenge. Besides, comprehensive experiment result also demonstrate the compelling effectiveness of our proposed method. The code is publicly available: https://github.com/movingforward100/Shadow_R.