Simultaneous Diffusion Sampling for Conditional LiDAR generation
Faulkner, Ryan Doan, Anh-Dzung Ratcliffe, Simon Haub, Luke Reid, Ian Chin, Tat-Jun
Faulkner, Ryan
Doan, Anh-Dzung
Ratcliffe, Simon
Haub, Luke
Reid, Ian
Chin, Tat-Jun
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
License
Language
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
By enabling capturing of 3D point clouds that reflect the geometry of the immediate environment, LiDAR has emerged as a primary sensor for autonomous systems. If a LiDAR scan is too sparse, occluded by obstacles, or too small in range, enhancing the point cloud scan by while respecting the geometry of the scene is useful for downstream tasks. Motivated by the explosive growth of interest in generative methods in vision, conditional LiDAR generation is starting to take off. This paper proposes a novel simultaneous diffusion sampling methodology to generate point clouds conditioned on the 3D structure of the scene as seen from multiple views. The key idea is to impose multi-view geometric constraints on the generation process, exploiting mutual information for enhanced results. Our method begins by recasting the input scan to multiple new viewpoints around the scan, thus creating multiple synthetic LiDAR scans. Then, the synthetic and input LiDAR scans simultaneously undergo conditional generation according to our methodology. Results show that our method can produce accurate and geometrically consistent enhancements to point cloud scans, allowing it to outperform existing methods by a large margin in a variety of benchmarks.
Citation
R. Faulkner, A.-D. Doan, S. Ratcliffe, L. Haub, I. Reid, T.-J. Chin, "Simultaneous Diffusion Sampling for Conditional LiDAR generation," 2025, pp. 1-8.
Source
Conference
2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
Keywords
40 Engineering, 4013 Geomatic Engineering, 46 Information and Computing Sciences, 4607 Graphics, Augmented Reality and Games
Subjects
Source
2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
Publisher
IEEE