Skip to content
SPECIFICTION
Get listed

MatAnyone

github.com

WebLinuxSelf-hosted
Visit github.com
Spec score 7.3 #24 of 29 in AI Video Background Removers

Spec sheet

Purpose
MatAnyone is a human video matting framework designed for stable core-region semantics and fine-grained boundary details, with target assignment.Read 9 Oct 2026 · github.com
Product
MatAnyone is a practical human video matting framework that supports assigning a target and produces stable core regions and fine-grained boundary details.Read 4 Oct 2026 · github.com
Integrations
The project provides Hugging Face model loading and a Hugging Face demo, and references SAM2 as an example source of segmentation masks.Read 4 Oct 2026 · github.com
Security
The project pages opened do not state security or compliance certifications.Read 9 Oct 2026 · github.com
Support
The README invites questions by email at [email protected].Read 9 Oct 2026 · github.com
License
The S-Lab License 1.0 permits redistribution and use for non-commercial purposes under stated conditions; commercial use requires contacting the contributors.Read 9 Oct 2026 · github.com
Compute limit
Users can set a maximum input size; videos exceeding it are downsampled, and no maximum is set by default.Read 9 Oct 2026 · github.com
Inputs
Inference takes a video and a segmentation mask for its first frame; documented video formats include MP4, MOV, and AVI.Read 9 Oct 2026 · github.com
Inputs and outputs
Inference takes a video and its first-frame segmentation mask and outputs foreground and alpha videos.Read 4 Oct 2026 · github.com
Install
The documented setup clones the repository, creates a Conda environment with Python 3.8, and installs dependencies with pip.Read 9 Oct 2026 · github.com
Integration
The README documents loading the model from Hugging Face for inference and identifies a Hugging Face integration.Read 9 Oct 2026 · github.com
Interactive demo
The project offers a Gradio demo on Hugging Face and says it can also be launched locally, with target masks assigned through a few clicks.Read 9 Oct 2026 · github.com
Local setup
The repository documents installation with Conda and Python 3.8, plus an optional dependency set for the Gradio demo.Read 4 Oct 2026 · github.com
Multiple targets
The README documents processing multiple targets by supplying a separate mask for each target.Read 9 Oct 2026 · github.com
Outputs
The inference results include a foreground video and an alpha video, with an option to save per-frame images.Read 9 Oct 2026 · github.com
Related release
The repository points users to MatAnyone 2 as a newer release.Read 9 Oct 2026 · github.com
Research context
The repository identifies the work as a CVPR 2025 paper by researchers affiliated with NTU S-Lab and SenseTime Research.Read 9 Oct 2026 · github.com
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.Read 4 Oct 2026 · github.com
Resolution handling
Input resolution has no maximum by default, but users can set a maximum size that downsamples larger videos.Read 4 Oct 2026 · github.com
Security and trust
The project pages opened for this research do not state security certifications or compliance claims.Read 4 Oct 2026 · github.com
Video formats
The example inputs include MP4, MOV, and AVI video files.Read 4 Oct 2026 · github.com

Where Specifiction places it

Alternatives to MatAnyoneAll alternatives →