# MCG-NKU/E2FGVI

Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

Repository: https://github.com/MCG-NKU/E2FGVI
Canonical: https://ross.abutalabs.com/products/e2fgvi
Language: Python
License: NOASSERTION
License Family: other
Topics: inpainting, optical-flow, cvpr2022, video-inpainting, object-removal
Last push: 2023-04-07T08:55:34+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": 1626, "days_push": 1244, "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 1161, forks 117 (observed 2026-08-28T04:03:49.262594+00:00)

## What it is
E2FGVI is the official PyTorch implementation of the CVPR 2022 paper 'Towards An End-to-End Framework for Flow-Guided Video Inpainting'. It fills in masked or missing regions in videos using optical-flow-guided deep learning, including a high-resolution variant (E2FGVI-HQ) that handles arbitrary resolutions.

## Use cases
- remove unwanted objects from a video
- fill in missing or masked regions in video frames
- repair damaged areas in footage
- video inpainting research baseline
- inpaint high-resolution videos with a pretrained model
- reproduce CVPR 2022 video inpainting results on DAVIS and YouTube-VOS

## When to choose
- you need state-of-the-art flow-guided video inpainting with pretrained weights
- you want to remove objects or fill holes across video frames with temporal consistency
- you need a research baseline or reference implementation for a paper
- you need to inpaint videos at arbitrary resolutions

## When to avoid
- you only need single-image inpainting rather than video
- you need a production-ready service with an API rather than research code
- you lack a GPU or cannot work with PyTorch training/inference pipelines
- you need a permissively licensed library since the license is non-standard

## Facets
- artifact type: library
- maturity: stable
- function: image-processing, computer-vision, deep-learning, video-processing
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python, cross-platform
- tags: video-inpainting, optical-flow, object-removal, pytorch, cvpr2022, research-code, pretrained-models, video, gpu, linux

## Member repositories
- MCG-NKU/E2FGVI (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:49.262594+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 2026-08-30T06:31:41.098915+00:00, confidence not recorded.
  - readme: https://github.com/MCG-NKU/E2FGVI (fetched 2026-08-28T04:03:49.262594+00:00, sha 6883017e5a78)
- Data as of 2026-08-30T08:39:29.467469+00:00.