cs.CVNov 10, 2026

FreeDeshadow: Shadow Removal for User-Specified Objects With Multimodal Prompts

Authors: Zhiliang Wu, Jihao Gu, Kun Li, Hanyu Xuan, Hehe Fan, Meng Wang, Weisi Lin

Organizations: College of Computing and Data Science, Nanyang Technological University, Singapore 639798, Singapore. · Department of Computer Science, University College London, London WC1E 6BT, U.K. · College of Computing and Artificial Intelligence, United Arab Emirates University, Abu Dhabi 15551, United Arab Emirates. · School of Big Data and Statistics, Anhui University, Hefei 230039, China. · 

Abstract

Existing shadow removal methods either perform global shadow removal or rely on precise shadow masks to guide restoration. Such paradigms limit their ability to selectively remove the shadow cast by a user-specified object in practical applications. To this end, we introduce an object-aware controllable shadow removal task, which allows users to specify a target object through a simple prompt and removes only its cast shadow while preserving other content. However, object-shadow asymmetry makes it challenging to establish accurate correspondence between the specified object and its spatially separated cast shadow and to confine restoration to the target shadow region. To address these challenges, we propose FreeDeshadow, a unified controllable shadow removal framework that supports both visual and textual prompts. It consists of an object-aware generator and a shadow-aware local refiner. The former interprets the user prompt and produces a high-quality shadow-free proposal, while the latter establishes the correspondence between the object and its cast shadow and constrains the generated changes to the target shadow region. To support training and evaluation, we further construct PCSRD+, a large-scale dataset containing 154,571 quadruples at 1024×\times1024 resolution and covering six types of user prompts. The visual prompts include a dot, a line, and an object mask, while the textual prompts describe the target object using attributes, spatial relations, or states. Extensive experiments demonstrate that FreeDeshadow accurately removes the shadow of the target object under both visual and textual prompts while effectively preserving non-target regions. It also outperforms existing methods in shadow removal performance and controllability. Project Page: https://wzlwlm13.github.io/FreeDeshadow

Figures & tables

Explore similar work

CardsList
  1. ODDR: One-Step Deshadow Diffusion via Reward Guidance

    Oct 1, 2026Junseong Shin, Kijun Kim, Minseong Kim +2Synthetic-to-Real Domain AdaptationDiffusion Models for Image Restoration

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

    Jul 29, 2026Yinan Wang, Yan Huang, Yong Xu +1Diffusion Models for Image RestorationShadow Removal

  3. After a Decade: Bringing Shadow Removal into the Real World with Agentic Training Data

    Sep 29, 2026Shilin Hu, Jingyi Xu, Dimitris Samaras +1Synthetic Data AugmentationShadow Removal