TopoDiT-3D: Topology-Aware Diffusion Transformer with Bottleneck Structure for 3D Point Cloud Generation


ZechaoGuan (Southeast University), Feng Yan (Meituan Company), Shuai Du (Southeast University), Lin Ma (Meituan Company), Qingshan Liu (Southeast University)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Recent advancements in Diffusion Transformer (DiT) models have significantly improved 3D point cloud generation. However, existing methods primarily focus on local feature extraction while overlooking global topological information, such as voids, which are crucial for maintaining shape consistency and capturing complex geometries. To address this limitation, we propose TopoDiT-3D, a Topology-Aware Diffusion Transformer with a bottleneck structure for 3D point cloud generation. Specifically, we design the bottleneck structure utilizing Perceiver Resampler, which not only offers a mode to integrate topological information extracted through persistent homology into feature learning, but also adaptively filters out redundant local features to improve training efficiency. Experimental results demonstrate that TopoDiT-3D outperforms state-of-the-art models in visual quality, diversity, and training efficiency. Furthermore, TopoDiT-3D demonstrates the importance of rich topological information for 3D point cloud generation and its synergy with conventional local feature learning.

Citation

@inproceedings{ZechaoGuan_2025_BMVC,
author    = {ZechaoGuan and Feng Yan and Shuai Du and Lin Ma and Qingshan Liu},
title     = {TopoDiT-3D: Topology-Aware Diffusion Transformer with Bottleneck Structure for 3D Point Cloud Generation},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_627/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection