| title | SAM2Matting: Generalized Image and Video Matting |
|---|---|
| authors | Ruiqi Shen, Guangquan Jie, Chang Liu, Henghui Ding |
| date | 2026-06-25 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.27339 |
| affiliation | FudanCVL |
| upvotes | 9 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Despite impressive advances in image matting, video matting remains challenging due to the inherent gap between high-level tracking, which requires frame-wise understanding, and low-level matting, which focuses on extremely fine-grained details. Existing methods attempt this with expensive and narrowly-scoped video matting datasets, which may limit out-of-domain generalization and compromise tracking robustness. We rethink the paradigm with SAM2Matting, a tracker-to-matting framework that advances VOS trackers to high-fidelity video matting. Specifically, it decouples the task by enhancing a foundational tracker (e.g., SAM2, SAM3) with a region-proposal bridge and dedicated matting heads, enabling the uncompromised tracker to handle temporal consistency while the matting components resolve fine-grained details. Notably, despite being trained only on images, SAM2Matting establishes new state-of-the-art performance on video matting, supports diverse prompt types, maintains strong temporal consistency, and demonstrates robust generalization across both human-centric and in-the-wild scenarios. |
cite
@misc{shen2026sam,
title={SAM2Matting: Generalized Image and Video Matting},
author={Ruiqi Shen and Guangquan Jie and Chang Liu and Henghui Ding},
year={2026},
eprint={2606.27339},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.27339}
}