发表机构
School of Computer Science and Engineering, South China University of Technology; Pazhou Lab; Polytech Nantes, Université de Nantes（华南理工大学计算机科学与工程学院; 琶洲实验室; 南特大学南特理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FreeShadow是基于预训练扩散模型的无需训练去阴影方法，通过光照迁移注意力等技术解决传统方法泛化差、易生伪影等问题，实验表明其泛化能力强且生成图像逼真。
AI 中文摘要
现有有监督和无监督去阴影方法因可用训练数据集多样性不足而泛化能力有限，而零样本方法易产生伪影且需耗时的测试时优化。为解决这些问题，我们提出FreeShadow，一种基于预训练扩散模型的无需训练的去阴影方法，利用扩散先验实现去阴影，无需任何训练或优化。针对光照恢复，我们提出光照迁移注意力（ITA），通过重新加权扩散模型中的自注意力图，将非阴影区域的光照线索迁移至阴影区域。针对内容保留，我们分析了光照变化对扩散模型中自注意力图和潜在高频特征的影响，选择性保留光照不变成分以维持内容保真度，同时抑制残留阴影。我们还提出局部纹理保持重光照（LTPR）以缓解VAE压缩导致的局部纹理错位。大量实验表明，我们的方法实现了强泛化能力，并生成逼真的无阴影图像。
英文摘要
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.
