astra-vision/LiDPM
[IV 2025, Oral] Official code of "LiDPM: Rethinking Point Diffusion for Lidar Scene Completion"
This project helps self-driving car engineers and robotics researchers complete partial LiDAR sensor scans, which often have gaps due to obstructions or sensor limitations. It takes in incomplete LiDAR point cloud data from real-world driving or robotics scenarios and outputs a densified, more complete representation of the environment. This is ideal for those working on autonomous navigation, perception, and environmental mapping.
No commits in the last 6 months.
Use this if you need to accurately fill in missing data points in LiDAR scans to create a more comprehensive and reliable 3D understanding of an environment for autonomous systems.
Not ideal if you are looking for a solution to process camera images or radar data, as this is specifically designed for LiDAR point cloud completion.
Stars
82
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/astra-vision/LiDPM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...