Romanelis, I., Fotis, V., Kalogeras, A., Alexakos, C., Munteanu, A., & Moustakas, K. (2026). Efficient and Scalable Point Cloud Generation With Sparse Point-Voxel Diffusion Models. IEEE Transactions on Neural Networks and Learning Systems, 37(6), 2607-2618. https://doi.org/10.1109/TNNLS.2025.3636409

@article{a55536267a5140d39ecbcff3588cfc88,
title = "Efficient and Scalable Point Cloud Generation With Sparse Point-Voxel Diffusion Models",
abstract = "We propose a novel point cloud U-Net diffusion architecture for 3-D generative modeling capable of generating high-quality and diverse 3-D 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 nondiffusion 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 point-voxel diffusion (PVD), measured on the same hardware setting. 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",
keywords = "Completion, Computational modeling, Computer architecture, Diffusion models, Feature extraction, Noise reduction, Pipelines, Point cloud compression, Shape, Superresolution, Three-dimensional displays, Deep learning, Diffusion, Generation, Generative modeling, Point clouds, Super-resolution",
author = "Ioannis Romanelis and Vlassis Fotis and Athanasios Kalogeras and Christos Alexakos and Adrian Munteanu and Konstantinos Moustakas",
year = "2026",
month = jun,
doi = "10.1109/TNNLS.2025.3636409",
language = "English",
volume = "37",
pages = "2607--2618",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computational Intelligence Society",
number = "6",
}