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

arXiv: https://arxiv.org/abs/2607.26715 · HTML: https://mlsanity.com/paper/2607.26715/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 30)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022)
- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [Deblurring via Stochastic Refinement](https://mlsanity.com/paper/2112.02475/) (2021)
- [ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal](https://mlsanity.com/paper/2212.04711/) (2022)
- [Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon](https://mlsanity.com/paper/2203.03818/) (2022)
- [Shadow Removal via Shadow Image Decomposition](https://mlsanity.com/paper/1908.08628/) (2019)
- [Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data](https://mlsanity.com/paper/1903.10683/) (2019)
- [DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network](https://mlsanity.com/paper/2207.10434/) (2022)
- [From Shadow Segmentation to Shadow Removal](https://mlsanity.com/paper/2008.00267/) (2020)
- [From Shadow Generation to Shadow Removal](https://mlsanity.com/paper/2103.12997/) (2021)
- [Portrait Shadow Manipulation](https://mlsanity.com/paper/2005.08925/) (2020)
- [DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity](https://mlsanity.com/paper/2211.08089/) (2022)
- [Latent Feature-Guided Diffusion Models for Shadow Removal](https://mlsanity.com/paper/2312.02156/) (2023)
- [Recasting Regional Lighting for Shadow Removal](https://mlsanity.com/paper/2402.00341/) (2024)
- [StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer](https://mlsanity.com/paper/2501.11319/) (2025)
- [OmniSR: Shadow Removal under Direct and Indirect Lighting](https://mlsanity.com/paper/2410.01719/) (2024)
- [Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/1803.02563/) (2018)
- [Detail-Preserving Latent Diffusion for Stable Shadow Removal](https://mlsanity.com/paper/2412.17630/) (2024)
- [Diff-Shadow: Global-guided Diffusion Model for Shadow Removal](https://mlsanity.com/paper/2407.16214/) (2024)
- [Generative Portrait Shadow Removal](https://mlsanity.com/paper/2410.05525/) (2024)
- [Single-Image Shadow Removal Using Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2407.08865/) (2024)
- [Training-Free Style and Content Transfer by Leveraging U-Net Skip Connections in Stable Diffusion](https://mlsanity.com/paper/2501.14524/) (2025)
- [Hyper RPCA: Joint Maximum Correntropy Criterion and Laplacian Scale Mixture Modeling On-the-Fly for Moving Object Detection](https://mlsanity.com/paper/2006.07795/) (2020)

## Abstract (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.