# zllrunning/video-object-removal

Just draw a bounding box and you can remove the object you want to remove.

Repository: https://github.com/zllrunning/video-object-removal
Canonical: https://ross.abutalabs.com/products/video-object-removal
Language: Python
License: MIT
License Family: permissive
Topics: pytorch, inpainting, video-inpainting, image-inpainting, object-removal
Last push: 2019-09-27T14:16:03+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2619, "days_push": 2532, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2711, forks 468 (observed 2026-08-28T04:07:11.840044+00:00)

## What it is
A PyTorch application that removes objects from videos by drawing a bounding box around them. It combines SiamMask for object tracking and segmentation with Deep-Video-Inpainting to fill in the removed regions.

## Use cases
- remove unwanted objects from a video clip
- erase a person from footage by drawing a box
- inpaint missing regions in video frames
- clean up background distractions in recorded video
- segment and track an object then delete it from the scene

## When to choose
- you need a simple draw-a-box workflow to delete objects from videos
- you have an NVIDIA GPU and can run PyTorch models locally
- you want to combine tracking-based segmentation with deep video inpainting

## When to avoid
- you need a polished GUI or production-ready tool
- you work on Windows or without a CUDA GPU
- you need state-of-the-art inpainting quality on modern models
- you need active maintenance or recent updates

## Facets
- artifact type: application
- maturity: maintenance
- function: computer-vision, image-processing, video-processing, machine-learning
- domain: computer-vision, image-processing, deep-learning
- platform: python
- tags: video-inpainting, object-removal, object-tracking, siammask, pytorch, bounding-box, video, linux, gpu

## Member repositories
- zllrunning/video-object-removal (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:11.840044+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:15:35.714445+00:00, confidence not recorded.
  - readme: https://github.com/zllrunning/video-object-removal (fetched 2026-08-28T04:07:11.840044+00:00, sha 46b858bc97c3)
- Data as of 2026-08-30T08:39:29.467469+00:00.