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

2026-07-28

AI Summary

This work addresses the challenges of video shadow removal in real-world scenarios, including complex illumination, diverse shadow appearances, and limited training data, by proposing a detail-preserving video diffusion framework. Built upon a pretrained video diffusion model, the approach employs LoRA fine-tuning while freezing the VAE decoder to enhance stability. It introduces a shadow mask-guided frequency decomposition modulation mechanism and a detail injection module to suppress shadow artifacts while preserving high-frequency textures. Monocular depth priors from Depth Anything V3 are incorporated to improve geometric awareness. Additionally, the authors construct WildShadow, the first large-scale outdoor video shadow removal dataset. Experiments demonstrate that the proposed method significantly outperforms existing approaches in terms of shadow removal quality, temporal consistency, and generalization capability.

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.

Problem

• video shadow removal
• in-the-wild
• complex illumination
• diverse shadow appearances
• limited training data

Innovation

• video shadow removal
• diffusion models
• detail preservation
• frequency modulation
• monocular depth prior