# vt-vl-lab/FGVC

[ECCV 2020] Flow-edge Guided Video Completion

Repository: https://github.com/vt-vl-lab/FGVC
Canonical: https://ross.abutalabs.com/products/fgvc
Language: Python
License: NOASSERTION
License Family: other
Last push: 2021-12-14T05:49:53+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2184, "days_push": 1723, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1551, forks 255 (observed 2026-08-28T04:05:02.203536+00:00)

## What it is
FGVC is a PyTorch implementation of the ECCV 2020 paper 'Flow-edge Guided Video Completion'. It completes missing regions in videos by extracting and completing motion edges to guide piecewise-smooth optical flow completion, supporting object removal and field-of-view extrapolation.

## Use cases
- remove unwanted objects from a video
- fill in missing or masked regions in video footage
- extrapolate video beyond its original field of view
- complete video content across motion boundaries
- compare video inpainting algorithms on DAVIS
- repair occluded areas in video sequences

## When to choose
- you need research-grade video completion with sharp motion boundaries
- you want to remove objects or extend the frame of a video using optical flow
- you are reproducing or building on the ECCV 2020 FGVC paper

## When to avoid
- you need a polished GUI application for casual video editing
- you require real-time video processing
- you need production support or active maintenance
- you work outside Linux or lack a GPU

## Facets
- artifact type: library
- maturity: maintenance
- function: video-processing, computer-vision, machine-learning, image-processing
- domain: computer-vision, machine-learning, deep-learning
- platform: python
- tags: video-completion, object-removal, video-inpainting, flow-completion, video-extrapolation, eccv-2020, research-code, pytorch, video, linux, gpu

## Member repositories
- vt-vl-lab/FGVC (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:02.203536+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 2026-08-30T04:30:17.853816+00:00, confidence not recorded.
  - readme: https://github.com/vt-vl-lab/FGVC (fetched 2026-08-28T04:05:02.203536+00:00, sha 3e9eb02578b4)
- Data as of 2026-08-30T08:39:29.467469+00:00.