WildShadowRemover: In-the-Wild Video Shadow Removal via Detail-Preserving Video Diffusion Models

• URL: http://arxiv.org/abs/2607.26203v1
• Date: Tue, 28 Jul 2026 19:08:26 GMT
• Title: WildShadowRemover: In-the-Wild Video Shadow Removal via Detail-Preserving Video Diffusion Models
• Abstract summary: Video shadow removal in the wild remains challenging due to complex illumination, diverse shadow appearances, and limited training data.<n>We present WildShadowRemover, a framework that adapts a pretrained video diffusion model for robust video shadow removal via LoRA fine-tuning.<n>We also construct WildShadow, a large-scale paired video shadow removal dataset and benchmark, covering diverse synthetic scenes.
• Score: 32.587071160357866
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video shadow removal in the wild remains challenging due to complex illumination, diverse shadow appearances, and limited training data. Despite its importance to numerous vision and graphics applications, it remains largely unexplored in unconstrained real-world scenarios. To address this gap, we present WildShadowRemover, a framework that adapts a pretrained video diffusion model for robust video shadow removal via LoRA fine-tuning. To preserve fine image details while retaining the model's powerful generative prior, we augment the frozen VAE decoder with a detail injection module and introduce a shadow-mask-guided frequency-decomposed modulation module to selectively restore high-frequency textures while suppressing shadow artifacts. Monocular depth priors from Depth Anything 3 further provide geometry-aware guidance under challenging lighting conditions. We also construct WildShadow, a large-scale paired video shadow removal dataset and benchmark, covering diverse synthetic scenes. Extensive experiments demonstrate that our method outperforms existing approaches in shadow removal quality and temporal consistency, producing temporally coherent shadow-free videos with superior visual quality and strong generalization across challenging in-the-wild scenarios.

Related papers

• FreeShadow: Training-Free Shadow Removal via Illumination Transfer and Selective Content Preservation in Diffusion Models [28.689075673734354]
  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.
  arXiv  Detail & Related papers  (2026-07-29T10:05:36Z)
• RelightVid: Temporal-Consistent Diffusion Model for Video Relighting [95.10341081549129]
  RelightVid is a flexible framework for video relighting.<n>It can accept background video, text prompts, or environment maps as relighting conditions.<n>It achieves arbitrary video relighting with high temporal consistency without intrinsic decomposition.
  arXiv  Detail & Related papers  (2025-01-27T18:59:57Z)
• MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis [64.00425120075045]
  Shadows are often under-considered or even ignored in image editing applications, limiting the realism of the edited results.<n>In this paper, we introduce MetaShadow, a three-in-one versatile framework that enables detection, removal, and controllable synthesis of shadows in natural images in an object-centered fashion.
  arXiv  Detail & Related papers  (2024-12-03T18:04:42Z)
• SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal [35.16957947180504]
  We introduce novel soft shadow masks specifically designed for shadow removal.<n>We propose a SoftShadow framework by leveraging the prior knowledge of pretrained SAM and integrating physical constraints.<n>This framework enables accurate predictions of penumbra (partially shaded) and umbra (fully shaded) areas while simultaneously facilitating end-to-end shadow removal.
  arXiv  Detail & Related papers  (2024-09-11T06:12:26Z)
• Soft-Hard Attention U-Net Model and Benchmark Dataset for Multiscale Image Shadow Removal [2.999888908665659]
  This study proposes a novel deep learning architecture, named Soft-Hard Attention U-net (SHAU), focusing on multiscale shadow removal. It provides a novel synthetic dataset, named Multiscale Shadow Removal dataset (MSRD), containing complex shadow patterns of multiple scales. The results demonstrate the effectiveness of SHAU over the relevant state-of-the-art shadow removal methods across various benchmark datasets.
  arXiv  Detail & Related papers  (2024-08-07T12:42:06Z)
• Single-Image Shadow Removal Using Deep Learning: A Comprehensive Survey [78.84004293081631]
  The patterns of shadows are arbitrary, varied, and often have highly complex trace structures. The degradation caused by shadows is spatially non-uniform, resulting in inconsistencies in illumination and color between shadow and non-shadow areas. Recent developments in this field are primarily driven by deep learning-based solutions.
  arXiv  Detail & Related papers  (2024-07-11T20:58:38Z)
• Learning Physical-Spatio-Temporal Features for Video Shadow Removal [42.95422940263425]
  We propose the first data-driven video shadow removal model, termedNet, by exploiting three essential characteristics of video shadows. Specifically, dedicated physical branch was established to conduct local illumination estimation, which is more applicable for scenes with complex lighting textures. To tackle the lack of datasets paired of shadow videos, we synthesize a dataset with aid of the popular game GTAV by controlling the switch of the shadow.
  arXiv  Detail & Related papers  (2023-03-16T14:55:31Z)
• 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)
• 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)
• Shadow-Aware Dynamic Convolution for Shadow Removal [80.82708225269684]
  We introduce a novel Shadow-Aware Dynamic Convolution (SADC) module to decouple the interdependence between the shadow region and the non-shadow region. Inspired by the fact that the color mapping of the non-shadow region is easier to learn, our SADC processes the non-shadow region with a lightweight convolution module. We develop a novel intra-convolution distillation loss to strengthen the information flow from the non-shadow region to the shadow region.
  arXiv  Detail & Related papers  (2022-05-10T14:00:48Z)
• Learning from Synthetic Shadows for Shadow Detection and Removal [43.53464469097872]
  Recent shadow removal approaches all train convolutional neural networks (CNN) on real paired shadow/shadow-free or shadow/shadow-free/mask image datasets. We present SynShadow, a novel large-scale synthetic shadow/shadow-free/matte image triplets dataset and a pipeline to synthesize it.
  arXiv  Detail & Related papers  (2021-01-05T18:56:34Z)
• 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.