FreeDeshadow: Shadow Removal for User-Specified Objects With Multimodal Prompts
Paper · https://arxiv.org/abs/2611.14608
arXiv:2611.14608v1 Announce Type: new 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$\times$1024 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
First seen by Oriel on .
AI summary
FreeDeshadow is a controllable shadow-removal framework that removes only the shadow cast by a user-specified object using visual or textual prompts.
- The object-aware generator interprets a prompt and produces a high-quality shadow-free proposal.
- The shadow-aware local refiner links the specified object to its spatially separated cast shadow and confines changes to that target region.
- PCSRD+ contains 154,571 quadruples at 1024×1024 resolution covering six prompt types.
- Visual prompts use a dot, line, or object mask, while textual prompts describe attributes, spatial relations, or states.
- Experiments report improved shadow-removal performance and controllability while preserving non-target regions.
#computer vision #shadow removal #multimodal prompts #image restoration
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| arXiv AI Papers | oai:arXiv.org:2611.14608v1 | https://arxiv.org/abs/2611.14608 Read discussion |