l1997i/LiM3D
🔥(CVPR 2023) Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation
This project helps autonomous driving engineers efficiently categorize objects in 3D LiDAR point cloud data. It takes raw 3D point cloud scans as input and outputs segmented scenes with objects like cars, pedestrians, and infrastructure clearly identified. This is ideal for professionals developing self-driving car systems who need accurate environmental understanding with reduced data annotation effort.
No commits in the last 6 months.
Use this if you need to perform semantic segmentation on 3D LiDAR point cloud data for applications like autonomous navigation, and want to achieve high accuracy with significantly less manually labeled training data and computational resources.
Not ideal if your application does not involve 3D LiDAR point clouds or if you require full supervision with extensive manual annotations.
Stars
98
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/l1997i/LiM3D"
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