Zarxrax/Sammie-Roto-2

A GUI for masking/rotoscoping video using AI models

What it solves

Sammie-Roto 2 is a desktop application designed to simplify the complex process of AI-assisted masking and rotoscoping in video clips. It provides a user-friendly interface for tasks that typically require tedious manual frame-by-frame editing.

How it works

The application integrates several specialized AI models to perform three primary functions:

  • Video Segmentation: Uses SAM2 and EfficientTAM to track and isolate objects across frames.
  • Video Matting: Employs MatAnyone, MatAnyone 2, and VideoMaMa to create high-quality, precise masks (mattes) for objects.
  • Video Object Removal: Utilizes MiniMax-Remover to remove unwanted elements from a video.

Who it’s for

It is intended for video editors and visual effects (VFX) artists who need a cross-platform tool for efficient object isolation and removal in video production.

Highlights

  • Cross-platform support: Available for Windows, Linux, and Mac.
  • Integrated Workflow: Combines segmentation, matting, and object removal in one tool.
  • Performance Optimizations: Supports half-precision for faster segmentation and includes various temporal stability improvements.
  • User-friendly Installation: Provides self-contained installers for easy setup on different operating systems.

Related

  • Project
    pq-yang/MatAnyone2

    A human video matting framework that preserves fine details and avoids coarse boundaries to extract people from videos with high robustness in real-world conditions.

  • Project
    pangxiaobin/image-matting

    A desktop application that uses the RMBG-1.4 model to provide local AI-powered background removal, batch processing, and image editing tools.

  • Project
    1038lab/ComfyUI-RMBG

    A ComfyUI custom node suite for advanced image background removal and precise object segmentation using a wide array of AI models like RMBG-2.0 and SAM2.

  • Project
    geekyutao/Inpaint-Anything

    A unified framework that combines SAM and generative inpainting models to remove, fill, or replace objects in images, videos, and 3D scenes.

  • Project
    opengeos/segment-geospatial

    A Python package that adapts the Segment Anything Model (SAM) for geospatial data, enabling easy segmentation of satellite imagery using text, points, or boxes.