paper-with-me

Papers

FreeShadow: Training-Free Shadow Removal via Illumination Transfer and Selective Content Preservation in Diffusion Models

2026-07-29 · Yinan Wang, Yan Huang, Yong Xu, Patrick Le Callet arxiv

Existing supervised and unsupervised shadow removal methods often suffer from limited generalization due to the insufficient diversity of available training datasets, while zero-shot methods tend to produce artifacts and require time-consuming test-time optimization. To address these issues, we propose FreeShadow, a training-free shadow removal method built upon pretrained diffusion models, which exploits diffusion priors for shadow removal without any training or optimization. For illumination recovery, we propose an illumination transfer attention (ITA), which re-weights the self-attention maps in diffusion model to transfer illumination cues from non-shadow to shadow regions. For content preservation, we analyze the effects of illumination variations on self-attention maps and latent high-frequency features in diffusion model, and selectively preserve illumination-invariant components to maintain content fidelity while suppressing residual shadows. We further propose local texture-preserving relighting (LTPR) to mitigate local texture misalignment caused by VAE compression. Extensive experiments demonstrate that our method achieves strong generalization and produces realistic shadow-free images.

📄 PDF Abstract BibTeX arXiv:2607.26715

Code (0)

등록된 구현이 없습니다.

Tasks

Shadow Removal

Similar Papers 제목 키워드 기반

OmniSR: Shadow Removal under Direct and Indirect Lighting

2024-10-02 · Jiamin Xu, Zelong Li, Yuxin Zheng, Chenyu Huang 외

Shadows can originate from occlusions in both direct and indirect illumination. Although most current shadow removal research focuses on shadows caused by direct illumination, shadows from indirect illumination are often…

Image Shadow RemovalShadow Removal

RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removal

2019-11-20 · Ling Zhang, Chengjiang Long, Xiaolong Zhang, Chunxia Xiao

Residual images and illumination estimation have been proved very helpful in image enhancement. In this paper, we propose a general and novel framework RIS-GAN which explores residual and illumination with Generative Adv…

Image EnhancementShadow Removal

Retinex-guided Histogram Transformer for Mask-free Shadow Removal

2025-04-18 · Wei Dong, Han Zhou, Seyed Amirreza Mousavi, Jun Chen

While deep learning methods have achieved notable progress in shadow removal, many existing approaches rely on shadow masks that are difficult to obtain, limiting their generalization to real-world scenes. In this work, …

Shadow Removal

Efficient Model-Driven Network for Shadow Removal

2022-02-01 · AAAI 2022 2 · Yurui Zhu, Zeyu Xiao, Yanchi Fang, Xueyang Fu 외

Abstract: Deep Convolutional Neural Networks (CNNs)-based methods have achieved significant breakthroughs in the task of single image shadow removal. However, the performance of these methods remains limited for several …

Image Shadow RemovalmodelShadow Removal

Physics-based Shadow Image Decomposition for Shadow Removal

2020-12-23 · Hieu Le, Dimitris Samaras

We propose a novel deep learning method for shadow removal. Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow ima…

Shadow Removal