Journal article · 2025 · Open access
Efficient and Scalable Point Cloud Generation With Sparse Point-Voxel Diffusion Models
IEEE Transactions on Neural Networks and Learning Systems, 37(6), 2607–2618 · Published 4 December 2025 · DOI 10.1109/tnnls.2025.3636409
In brief
“Efficient and Scalable Point Cloud Generation With Sparse Point-Voxel Diffusion Models” is a 2025 journal article by Ioannis Romanelis and 5 co-authors, published in IEEE Transactions on Neural Networks and Learning Systems. OpenAlex counts 21 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Neural Networks and Learning Systems.
- Citations
- 21
- Most cited in
- 2026 (14)
- Field-weighted impact
- 6.15
- References
- 70
- Authors
- 6
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.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Romanelis, I., Fotis, V., Kalogeras, A. P., Alexakos, C., Munteanu, A., & Μουστάκας, Κ. (2025). 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
MLA 9
Romanelis, Ioannis, et al. “Efficient and Scalable Point Cloud Generation With Sparse Point-Voxel Diffusion Models.” IEEE Transactions on Neural Networks and Learning Systems, vol. 37, no. 6, 2025, pp. 2607–2618. https://doi.org/10.1109/tnnls.2025.3636409.
Chicago
Romanelis, Ioannis, Vlassis Fotis, Athanasios P. Kalogeras, Christos Alexakos, Adrian Munteanu, and Κωνσταντίνος Μουστάκας. 2025. “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.
Harvard
Romanelis, I. et al. (2025) ‘Efficient and Scalable Point Cloud Generation With Sparse Point-Voxel Diffusion Models’, IEEE Transactions on Neural Networks and Learning Systems, 37(6), pp. 2607–2618. doi:10.1109/tnnls.2025.3636409.
IEEE
I. Romanelis, V. Fotis, A. P. Kalogeras, C. Alexakos, A. Munteanu, and Κ. Μουστάκας, “Efficient and Scalable Point Cloud Generation With Sparse Point-Voxel Diffusion Models,” IEEE Transactions on Neural Networks and Learning Systems, vol. 37, no. 6, pp. 2607–2618, 2025, doi: 10.1109/tnnls.2025.3636409.
BibTeX
@article{romanelis2025efficient,
title = {{Efficient and Scalable Point Cloud Generation With Sparse Point-Voxel Diffusion Models}},
author = {Romanelis, Ioannis and Fotis, Vlassis and Kalogeras, Athanasios P. and Alexakos, Christos and Munteanu, Adrian and Μουστάκας, Κωνσταντίνος},
journal = {IEEE Transactions on Neural Networks and Learning Systems},
year = {2025},
volume = {37},
number = {6},
pages = {2607--2618},
doi = {10.1109/tnnls.2025.3636409},
url = {https://doi.org/10.1109/tnnls.2025.3636409}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 1 | |
| 2025 | 6 | |
| 2026 | 14 |
Its field-weighted citation impact is 6.15: it has been cited 6.15 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis
- point cloud generation
- point cloud completion
- ShapeNet
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Romanelis, I., Fotis, V., Kalogeras, A. P., Alexakos, C., Munteanu, A., & Μουστάκας, Κ. (2025). 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
How many times has this paper been cited?
21 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at IEEE Transactions on Neural Networks and Learning Systems: sign in and open the full text from this page.
Who wrote this paper?
Ioannis Romanelis, Vlassis Fotis, Athanasios P. Kalogeras, Christos Alexakos, Adrian Munteanu, Κωνσταντίνος Μουστάκας.
What is the DOI of this paper?
10.1109/tnnls.2025.3636409, permanently at https://doi.org/10.1109/tnnls.2025.3636409. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.