MCG-NKU/E2FGVI

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1161 stars · 117 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity stable

image-processing computer-vision deep-learning video-processing computer-vision image-processing deep-learning machine-learning python cross-platform video-inpainting optical-flow object-removal pytorch cvpr2022 research-code pretrained-models video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="MCG-NKU/E2FGVI")