ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformer
This addresses shadow removal for computer vision applications like object detection and segmentation, offering a mask-free approach that is incremental in improving existing methods.
The paper tackles the problem of removing shadows from images without requiring masks, introducing ShadowRefiner, a network that uses Fast Fourier Transformer for spatial and frequency learning, and it won first place in the Perceptual Track and second in the Fidelity Track of the NTIRE 2024 Image Shadow Removal Challenge.
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.