Lilac-Lee/Neural_Scene_Flow_Prior
Neural Scene Flow Prior (NeurIPS 2021 spotlight)
This project helps robotics engineers and autonomous driving developers analyze how objects and scenes are moving in 3D space. It takes raw 3D point cloud data from sensors like LiDAR, and outputs a 'scene flow' — a precise measurement of motion for each point. This is crucial for tasks like motion prediction and obstacle avoidance.
138 stars. No commits in the last 6 months.
Use this if you need to accurately determine the 3D motion of objects or entire scenes from point cloud data, without requiring extensive pre-training on vast datasets.
Not ideal if your primary goal is real-time performance on resource-constrained embedded systems, although a faster version (FastNSF) is available.
Stars
138
Forks
14
Language
Python
License
MIT
Category
Last pushed
Apr 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Lilac-Lee/Neural_Scene_Flow_Prior"
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.