vzyrianov/lidargen
Official implementation of "Learning to Generate Realistic LiDAR Point Clouds" (ECCV 2022)
This project helps researchers and developers in autonomous driving or robotics generate realistic LiDAR point clouds for simulation and testing. It takes existing LiDAR scan data (like from KITTI-360) and outputs new, synthetic LiDAR point cloud data, which can be used to augment datasets or test algorithms in varied scenarios. This tool is for those who need to create diverse and realistic LiDAR data without extensive real-world collection.
149 stars. No commits in the last 6 months.
Use this if you need to create synthetic, realistic LiDAR point clouds to expand your datasets for training and evaluating autonomous driving or robotics systems.
Not ideal if you primarily work with other sensor data types or require only raw LiDAR data without the need for generative modeling.
Stars
149
Forks
13
Language
Python
License
MIT
Category
Last pushed
Sep 16, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/vzyrianov/lidargen"
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...