PRBonn/4DMOS
Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions (RAL 2022)
This tool helps autonomous vehicle developers, robotics engineers, or anyone working with LiDAR data to reliably distinguish between stationary and moving objects in real-time. It takes a sequence of 3D LiDAR point clouds and outputs a segmented point cloud where each point is labeled as either moving or non-moving, allowing for safer navigation and improved environmental understanding. This is crucial for developing robust self-driving cars and mobile robots.
329 stars. No commits in the last 6 months.
Use this if you need to accurately identify and segment moving objects from static background elements within streams of 3D LiDAR sensor data.
Not ideal if your primary need is general scene classification or object detection rather than the specific task of distinguishing dynamic from static objects.
Stars
329
Forks
32
Language
Python
License
MIT
Category
Last pushed
Aug 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/PRBonn/4DMOS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
drprojects/superpoint_transformer
Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D...
yuxumin/PoinTr
[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
charlesq34/frustum-pointnets
Frustum PointNets for 3D Object Detection from RGB-D Data
drprojects/DeepViewAgg
[CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in...
facebookresearch/votenet
Deep Hough Voting for 3D Object Detection in Point Clouds