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

• URL: http://arxiv.org/abs/2607.26715v1
• Date: Wed, 29 Jul 2026 10:05:36 GMT
• Title: FreeShadow: Training-Free Shadow Removal via Illumination Transfer and Selective Content Preservation in Diffusion Models
• Abstract summary: FreeShadow is a training-free shadow removal method built upon pretrained diffusion models.<n>Our method achieves strong generalization and produces realistic shadow-free images.
• Score: 28.689075673734354
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• ZeroIDIR: Zero-Reference Illumination Degradation Image Restoration with Perturbed Consistency Diffusion Models [72.4683657127516]
  We propose a zero-reference diffusion-based framework, named ZeroIDIR, for illumination image restoration.<n>The framework decouples the restoration process into adaptive illumination correction and diffusion-based reconstruction.<n>Experiments on publicly available benchmarks show that the proposed method outperforms state-of-the-art unsupervised competitors.
  arXiv  Detail & Related papers  (2026-05-12T02:36:49Z)
• Structure-Guided Diffusion Models for High-Fidelity Portrait Shadow Removal [34.35752953614944]
  We present a diffusion-based portrait shadow removal approach that can robustly produce high-fidelity results.<n>We first train a shadow-independent structure extraction network on a real-world portrait dataset with various synthetic lighting conditions.<n>The structure map is then used as condition to train a structure-guided inpainting diffusion model for removing shadows in a generative manner.
  arXiv  Detail & Related papers  (2025-07-07T06:19:07Z)
• Generative Portrait Shadow Removal [27.98144439007323]
  We introduce a high-fidelity portrait shadow removal model that can effectively enhance the image of a portrait. Our method also demonstrates robustness to diverse subjects captured in real environments.
  arXiv  Detail & Related papers  (2024-10-07T22:09:22Z)
• Retinex-Diffusion: On Controlling Illumination Conditions in Diffusion Models via Retinex Theory [19.205929427075965]
  We conceptualize the diffusion model as a black-box image render and strategically decompose its energy function in alignment with the image formation model. It generates images with realistic illumination effects, including cast shadow, soft shadow, and inter-reflections.
  arXiv  Detail & Related papers  (2024-07-29T03:15:07Z)
• Latent Feature-Guided Diffusion Models for Shadow Removal [47.21387783721207]
  We propose the use of diffusion models as they offer a promising approach to gradually refine the details of shadow regions during the diffusion process.<n>Our method improves this process by conditioning on a learned latent feature space that inherits the characteristics of shadow-free images.<n>We demonstrate the effectiveness of our approach which outperforms the previous best method by 13% in terms of RMSE on the AISTD dataset.
  arXiv  Detail & Related papers  (2023-12-04T18:59:55Z)
• SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and Illumination Removal in High-Illuminance Scenes [51.50157919750782]
  We present SIRe-IR, an implicit neural rendering inverse approach that decomposes the scene into environment map, albedo, and roughness. By accurately modeling the indirect radiance field, normal, visibility, and direct light simultaneously, we are able to remove both shadows and indirect illumination. Even in the presence of intense illumination, our method recovers high-quality albedo and roughness with no shadow interference.
  arXiv  Detail & Related papers  (2023-10-19T10:44:23Z)
• ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal [74.86415440438051]
  We propose a unified diffusion framework that integrates both the image and degradation priors for highly effective shadow removal. Our model achieves a significant improvement in terms of PSNR, increasing from 31.69dB to 34.73dB over SRD dataset.
  arXiv  Detail & Related papers  (2022-12-09T07:48:30Z)
• Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning [66.36104525390316]
  We propose a two-stage learning method, including reflectance guidance and a Shadow/Specular-Aware (S-Aware) network to tackle the problem. In the first stage, an initial reflectance layer free from shadows and specularities is obtained with the constraint of novel losses. To further enforce the reflectance layer to be independent of shadows and specularities in the second-stage refinement, we introduce an S-Aware network that distinguishes the reflectance image from the input image.
  arXiv  Detail & Related papers  (2022-11-27T07:26:41Z)
• DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity [54.831083157152136]
  We present a method that removes hard, soft and self shadows based on adaptive attention and ViT similarity. Our method outperforms state-of-the-art methods on the SRD, AISTD, LRSS, USR and UIUC datasets.
  arXiv  Detail & Related papers  (2022-11-15T12:15:29Z)
• Self-Supervised Shadow Removal [130.6657167667636]
  We propose an unsupervised single image shadow removal solution via self-supervised learning by using a conditioned mask. In contrast to existing literature, we do not require paired shadowed and shadow-free images, instead we rely on self-supervision and jointly learn deep models to remove and add shadows to images.
  arXiv  Detail & Related papers  (2020-10-22T11:33:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.