Fast LiDAR Upsampling using Conditional Diffusion Models

TL;DR

This paper presents a fast and high-quality LiDAR point cloud upsampling method using conditional diffusion models, enabling real-time performance for autonomous navigation and robotics.

Contribution

It introduces a novel conditional diffusion model approach for LiDAR upsampling that outperforms baselines in speed and quality, suitable for real-time applications.

Findings

Outperforms baselines in sampling speed and quality

Effective on multiple datasets including real-world and synthetic

Demonstrates generalization across different environments

Abstract

The search for refining 3D LiDAR data has attracted growing interest motivated by recent techniques such as supervised learning or generative model-based methods. Existing approaches have shown the possibilities for using diffusion models to generate refined LiDAR data with high fidelity, although the performance and speed of such methods have been limited. These limitations make it difficult to execute in real-time, causing the approaches to struggle in real-world tasks such as autonomous navigation and human-robot interaction. In this work, we introduce a novel approach based on conditional diffusion models for fast and high-quality sparse-to-dense upsampling of 3D scene point clouds through an image representation. Our method employs denoising diffusion probabilistic models trained with conditional inpainting masks, which have been shown to give high performance on image completion tasks. We introduce a series of experiments, including multiple datasets, sampling steps, and conditional masks. This paper illustrates that our method outperforms the baselines in sampling speed and quality on upsampling tasks using the KITTI-360 dataset. Furthermore, we illustrate the generalization ability of our approach by simultaneously training on real-world and synthetic datasets, introducing variance in quality and environments.