Home
Publications
Photo Gallery
MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis
Tianyu Wang, Jianming Zhang, Haitian Zheng, Zhihong Ding, Scott Cohen, Zhe Lin, Wei Xiong, Chi-Wing Fu, Luis Figueroa, Soo Ye Kim
CVPR · 2025 · Project Lead
Luis Figueroa: Co-corresponding author; Soo Ye Kim: Co-corresponding author
Research summary
A three-in-one framework for object-centered shadow detection, removal, and controllable synthesis in natural images.
Abstract
Shadows are often underconsidered or even ignored in image editing applications, limiting the realism of the edited results. 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. MetaShadow combines the strengths of two cooperative components: Shadow Analyzer, for object-centered shadow detection and removal, and Shadow Synthesizer, for reference-based controllable shadow synthesis. Notably, we optimize the learning of the intermediate features from Shadow Analyzer to guide Shadow Synthesizer to generate more realistic shadows that blend seamlessly with the scene. Extensive evaluations on multiple shadow benchmark datasets show significant improvements of MetaShadow over the existing state-of-the-art methods on object-centered shadow detection, removal, and synthesis. MetaShadow excels in supporting imageediting tasks such as object removal, relocation, and insertion, pushing the boundaries of object-centered image editing.
Key insight
First unified framework for object-centered shadow detection, removal, and controllable synthesis, enabling practical image editing tasks like object insertion and relocation with realistic shadow effects.
CVPR 2025 proceedings; arXiv preprint also available
Paper & resources
BibTeX
@inproceedings{wang2025metashadow,
title={MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis},
author={Wang, Tianyu and Zhang, Jianming and Zheng, Haitian and Ding, Zhihong and Cohen, Scott and Lin, Zhe and Xiong, Wei and Fu, Chi-Wing and Figueroa, Luis and Kim, Soo Ye},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2025}
}