kazuto1011/r2dm
LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models (ICRA 2024)
This project helps robotics engineers and researchers generate realistic LiDAR sensor data for tasks like autonomous vehicle development and environmental mapping. It takes an empty canvas and produces synthetic LiDAR scans, including both range (distance) and reflectance (intensity) information. This data can then be converted into a 3D point cloud, useful for training perception models or simulating various scenarios.
No commits in the last 6 months.
Use this if you need to create synthetic LiDAR data to augment your datasets, test algorithms without real-world scanning, or simulate complex environments for robotics applications.
Not ideal if you need to process or analyze existing LiDAR point clouds or require a tool for hardware-based LiDAR calibration.
Stars
69
Forks
8
Language
Python
License
MIT
Category
Last pushed
Jul 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/kazuto1011/r2dm"
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...