LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models
Kazuto Nakashima     Ryo Kurazume
Kyushu University
ICRA 2024
Project | Paper | Code

This is a demo of our paper "LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models" presented at ICRA 2024.
We propose R2DM, a continuous-time diffusion model for LiDAR data generation based on the equirectangular range/reflectance image representation.

Dataset
Sampler
Number of sampling steps (>256 is recommended)

To run this demo locally:

git clone https://huggingface.co/spaces/kazuto1011/r2dm

cd r2dm

pip install -r requirements.txt

pip install gradio

gradio app.py