MatAnyone
API—OSS—FREE—DOCS3/5
MA5.2#15 of 28
outWeb—Windows—Mac—Linux—Android—iOS
Ranked in AI Video Background Removers ·No free plan on record
About
MatAnyone is ranked #15 of 28 in AI video background removers on Inferse. It runs on Self-hosted, Web.
Compared on AI video background removers
- Foreground isolation
- Yesgithub.com
- Max export resolution
- 1080pgithub.com
- Video input formats
- .mp4, .mov, .avigithub.com
Facts
- Product
- MatAnyone is a practical human video matting framework that supports assigning a target and produces stable core regions and fine-grained boundary details.github.com · 4 Oct 2026
- Inputs and outputs
- Inference takes a video and its first-frame segmentation mask and outputs foreground and alpha videos.github.com · 4 Oct 2026
- Multiple targets
- The inference scripts support processing multiple targets by using separate masks.github.com · 4 Oct 2026
- Interactive demo
- The Gradio demo lets users upload a video or image and assign target masks with a few clicks; it can run on Hugging Face or locally.github.com · 4 Oct 2026
- Integrations
- The project provides Hugging Face model loading and a Hugging Face demo, and references SAM2 as an example source of segmentation masks.github.com · 4 Oct 2026
- Local setup
- The repository documents installation with Conda and Python 3.8, plus an optional dependency set for the Gradio demo.github.com · 4 Oct 2026
- Video formats
- The example inputs include MP4, MOV, and AVI video files.github.com · 4 Oct 2026
- Resolution handling
- Input resolution has no maximum by default, but users can set a maximum size that downsamples larger videos.github.com · 4 Oct 2026
- License
- The project uses the S-Lab License 1.0, which permits non-commercial use; commercial use requires contacting the contributors.github.com · 4 Oct 2026
- Security and trust
- The project pages opened for this research do not state security certifications or compliance claims.github.com · 4 Oct 2026
- Support
- The repository invites questions by email at [email protected].github.com · 4 Oct 2026
- Research context
- The project page identifies MatAnyone as a CVPR 2025 paper and lists the authors’ affiliations as S-Lab at Nanyang Technological University and SenseTime Research.pq-yang.github.io · 4 Oct 2026
- Research use
- The repository provides training instructions, evaluation scripts, benchmark data, and asks users to cite the CVPR paper when using the repository for research.github.com · 4 Oct 2026
Best MatAnyone alternatives
See all 20
Where it ranks on Inferse
Sources
- github.com/pq-yang/MatAnyone· checked 4 Oct 2026
- github.com/pq-yang/MatAnyone/blob/main/LICENSE· checked 4 Oct 2026
- pq-yang.github.io/projects/MatAnyone/· checked 4 Oct 2026