NewEvery arXiv paper, its researchers & institutions — mapped.
computer vision

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

arXiv:2607.26715

summary

FreeShadow removes shadows from images without any training by leveraging pretrained diffusion models, using illumination transfer attention to bring lighting cues from non‑shadow areas and preserving content through selective attention and texture‑preserving relighting.

Abstract

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.

Topics & keywords

#shadow removal#diffusion models#illumination transfer#zero-shot#image relightingillumination transfer attentionself-attention re-weightinglatent high‑frequency featureslocal texture‑preserving relightingpretrained diffusion priors