https://github.com/aaashrafhabib/raft

Implementation of RAFT (Recurrent All-Pairs Field Transforms) for dense optical flow estimation, using an all-pairs correlation volume and iterative refinement for precise motion prediction between video frames.
https://github.com/aaashrafhabib/raft

autoencoder computer-vision deep-neural-networks

Last synced: 5 months ago
JSON representation

Implementation of RAFT (Recurrent All-Pairs Field Transforms) for dense optical flow estimation, using an all-pairs correlation volume and iterative refinement for precise motion prediction between video frames.

• Host: GitHub
• URL: https://github.com/aaashrafhabib/raft
• Owner: AaashrafHabib
• Created: 2024-11-08T13:35:30.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-11-09T15:24:09.000Z (over 1 year ago)
• Last Synced: 2025-04-07T10:35:56.252Z (over 1 year ago)
• Topics: autoencoder, computer-vision, deep-neural-networks
• Language: Jupyter Notebook
• Homepage:
• Size: 24 MB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# RAFT

[Deep Architecture for Optical Flow Estimation RAFT.pdf](https://github.com/user-attachments/files/17687404/Deep.Architecture.for.Optical.Flow.Estimation.RAFT.pdf)