Contrast-Prior Enhanced Duality for Mask-Free Shadow Removal

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Jiyu, Liu, Yifan, Huang, Jiancheng, Yan, Mingfu, Chen, Shifeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914171088535552
author Wu, Jiyu
Liu, Yifan
Huang, Jiancheng
Yan, Mingfu
Chen, Shifeng
author_facet Wu, Jiyu
Liu, Yifan
Huang, Jiancheng
Yan, Mingfu
Chen, Shifeng
contents Existing shadow removal methods often rely on shadow masks, which are challenging to acquire in real-world scenarios. Exploring intrinsic image cues, such as local contrast information, presents a potential alternative for guiding shadow removal in the absence of explicit masks. However, the cue's inherent ambiguity becomes a critical limitation in complex scenes, where it can fail to distinguish true shadows from low-reflectance objects and intricate background textures. To address this motivation, we propose the Adaptive Gated Dual-Branch Attention (AGBA) mechanism. AGBA dynamically filters and re-weighs the contrast prior to effectively disentangle shadow features from confounding visual elements. Furthermore, to tackle the persistent challenge of restoring soft shadow boundaries and fine-grained details, we introduce a diffusion-based Frequency-Contrast Fusion Network (FCFN) that leverages high-frequency and contrast cues to guide the generative process. Extensive experiments demonstrate that our method achieves state-of-the-art results among mask-free approaches while maintaining competitive performance relative to mask-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21949
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Contrast-Prior Enhanced Duality for Mask-Free Shadow Removal
Wu, Jiyu
Liu, Yifan
Huang, Jiancheng
Yan, Mingfu
Chen, Shifeng
Computer Vision and Pattern Recognition
Artificial Intelligence
Existing shadow removal methods often rely on shadow masks, which are challenging to acquire in real-world scenarios. Exploring intrinsic image cues, such as local contrast information, presents a potential alternative for guiding shadow removal in the absence of explicit masks. However, the cue's inherent ambiguity becomes a critical limitation in complex scenes, where it can fail to distinguish true shadows from low-reflectance objects and intricate background textures. To address this motivation, we propose the Adaptive Gated Dual-Branch Attention (AGBA) mechanism. AGBA dynamically filters and re-weighs the contrast prior to effectively disentangle shadow features from confounding visual elements. Furthermore, to tackle the persistent challenge of restoring soft shadow boundaries and fine-grained details, we introduce a diffusion-based Frequency-Contrast Fusion Network (FCFN) that leverages high-frequency and contrast cues to guide the generative process. Extensive experiments demonstrate that our method achieves state-of-the-art results among mask-free approaches while maintaining competitive performance relative to mask-based methods.
title Contrast-Prior Enhanced Duality for Mask-Free Shadow Removal
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.21949