weiyithu/PV-RAFT
[CVPR 2021] PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds
This project helps developers working on 3D computer vision tasks to accurately track the movement of objects or points within a 3D environment. It takes in sequences of 3D point clouds (like those from LiDAR sensors or depth cameras) and outputs estimations of 'scene flow' — the 3D motion vectors for each point. Developers integrating 3D perception into robotics, autonomous vehicles, or augmented reality applications would use this.
No commits in the last 6 months.
Use this if you are a researcher or engineer building advanced 3D perception systems and need to estimate dense motion in point cloud data.
Not ideal if you are looking for a plug-and-play solution for basic 3D object tracking without specialized hardware or deep learning expertise.
Stars
80
Forks
9
Language
Python
License
MIT
Category
Last pushed
Jul 28, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/weiyithu/PV-RAFT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
3DOM-FBK/deep-image-matching
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM...
suhangpro/mvcnn
Multi-view CNN (MVCNN) for shape recognition
zouchuhang/LayoutNet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a...
andyzeng/tsdf-fusion-python
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
andyzeng/tsdf-fusion
Fuse multiple depth frames into a TSDF voxel volume.