Lilac-Lee/FastNSF
Fast Neural Scene Flow (ICCV 2023)
This project helps researchers and engineers analyze motion in dynamic 3D environments, particularly those working with LiDAR data. It takes in sequences of 3D point cloud data and outputs highly accurate 3D scene flow estimations, which describe how points in a scene are moving. This is useful for anyone developing or evaluating autonomous driving systems, robotics, or other applications requiring precise understanding of object movement.
No commits in the last 6 months.
Use this if you need to quickly and accurately estimate 3D motion from LiDAR point clouds, especially for autonomous navigation or robotics.
Not ideal if your primary need is not 3D motion estimation from dense point clouds, or if you are working with simpler image-based motion tasks.
Stars
77
Forks
6
Language
Python
License
MIT
Category
Last pushed
Oct 26, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Lilac-Lee/FastNSF"
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.