kavisha725/MBNSF
[3DV 2024] Repository for "Multi-Body Neural Scene Flow", in International Conference on 3D Vision 2024.
This project helps computer vision researchers and robotics engineers evaluate advanced methods for understanding movement in 3D environments. It takes sequences of 3D point clouds, typically from LiDAR sensors on autonomous vehicles, and accurately estimates how objects and the scene are moving over time. The output is a highly precise measurement of scene flow and 4D trajectories, crucial for developing robust perception systems.
No commits in the last 6 months.
Use this if you are a researcher or engineer working on 3D scene understanding for autonomous systems and need to evaluate state-of-the-art methods for 3D scene flow and object trajectory estimation using real-world LiDAR data.
Not ideal if you are looking for a pre-trained, plug-and-play solution for general object tracking or if you don't have experience with deep learning research environments.
Stars
14
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/kavisha725/MBNSF"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vita-epfl/monoloco
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social...
fangchangma/self-supervised-depth-completion
ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and...
nburrus/stereodemo
Small Python utility to compare and visualize the output of various stereo depth estimation algorithms
JiawangBian/sc_depth_pl
SC-Depth (V1, V2, and V3) for Unsupervised Monocular Depth Estimation ...
wvangansbeke/Sparse-Depth-Completion
Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st...