nbei/Deep-Flow-Guided-Video-Inpainting
A CVPR 2019 PyTorch implementation for video inpainting using optical flow to guide generative filling of masked objects in videos.
Not currently ranked — collecting fresh signals.
star history
This repository provides an implementation of deep flow-guided video inpainting, combining optical flow estimation (FlowNet2), deep learning-based image inpainting (Deepfillv1), and propagation techniques to remove objects from videos. The system takes video frames and masks as input and generates inpainted video output by flowing content from surrounding frames into masked regions.
Frequently asked
- What is nbei/Deep-Flow-Guided-Video-Inpainting?
- A CVPR 2019 PyTorch implementation for video inpainting using optical flow to guide generative filling of masked objects in videos.
- Is Deep-Flow-Guided-Video-Inpainting open source?
- Yes — nbei/Deep-Flow-Guided-Video-Inpainting is open source, released under the MIT license.
- What language is Deep-Flow-Guided-Video-Inpainting written in?
- nbei/Deep-Flow-Guided-Video-Inpainting is primarily written in Python.
- How popular is Deep-Flow-Guided-Video-Inpainting?
- nbei/Deep-Flow-Guided-Video-Inpainting has 2.4k stars on GitHub.
- Where can I find Deep-Flow-Guided-Video-Inpainting?
- nbei/Deep-Flow-Guided-Video-Inpainting is on GitHub at https://github.com/nbei/Deep-Flow-Guided-Video-Inpainting.