2024/08/12 by Ioannis Romanelis, Vlassios Fotis, Romanelis, Ioannis +9 · 2 citations
Computer Science · Engineering · Mathematics · #3D Shape Modeling and Analysis #Artificial intelligence #Cloud computing #Computational science #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Database #Diffusion #FOS: Computer and information sciences #Geometry #Image Processing and 3D Reconstruction #Mathematics #Operating system #Physics #Point (geometry) #Point cloud #Scalability #Voxel
paper · pdf · doi:10.48550/arxiv.2408.06145
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/08/12 · openalex created_date 2024/09/10 · openalex updated_date 2026/07/28
We propose a novel point cloud U-Net diffusion architecture for 3D generative modeling capable of generating high-quality and diverse 3D shapes while maintaining fast generation times. Our network employs a dual-branch architecture, combining the high-resolution representations of points with the computational efficiency of sparse voxels. Our fastest variant outperforms all non-diffusion generative approaches on unconditional shape generation, the most popular benchmark for evaluating point cloud generative models, while our largest model achieves state-of-the-art results among diffusion methods, with a runtime approximately 70% of the previously state-of-the-art PVD. Beyond unconditional generation, we perform extensive evaluations, including conditional generation on all categories of ShapeNet, demonstrating the scalability of our model to larger datasets, and implicit generation which allows our network to produce high quality point clouds on fewer timesteps, further decreasing the generation time. Finally, we evaluate the architecture's performance in point cloud completion and super-resolution. Our model excels in all tasks, establishing it as a state-of-the-art diffusion U-Net for point cloud generative modeling. The code is publicly available at https://github.com/JohnRomanelis/SPVD.git.