Fast LiDAR Upsampling using Conditional Diffusion Models

arXiv:2405.04889v1 Announce Type: new
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 …

abstract arxiv cs.cv cs.ro data diffusion diffusion models fidelity generate generative lidar performance search speed supervised learning type