StrucADT: Generating Structure-controlled 3D Point Clouds with Adjacency Diffusion Transformer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914061884588032 |
|---|---|
| author | Shu, Zhenyu Shen, Jiajun Chen, Zhongui Han, Xiaoguang Xin, Shiqing |
| author_facet | Shu, Zhenyu Shen, Jiajun Chen, Zhongui Han, Xiaoguang Xin, Shiqing |
| contents | In the field of 3D point cloud generation, numerous 3D generative models have demonstrated the ability to generate diverse and realistic 3D shapes. However, the majority of these approaches struggle to generate controllable 3D point cloud shapes that meet user-specific requirements, hindering the large-scale application of 3D point cloud generation. To address the challenge of lacking control in 3D point cloud generation, we are the first to propose controlling the generation of point clouds by shape structures that comprise part existences and part adjacency relationships. We manually annotate the adjacency relationships between the segmented parts of point cloud shapes, thereby constructing a StructureGraph representation. Based on this StructureGraph representation, we introduce StrucADT, a novel structure-controllable point cloud generation model, which consists of StructureGraphNet module to extract structure-aware latent features, cCNF Prior module to learn the distribution of the latent features controlled by the part adjacency, and Diffusion Transformer module conditioned on the latent features and part adjacency to generate structure-consistent point cloud shapes. Experimental results demonstrate that our structure-controllable 3D point cloud generation method produces high-quality and diverse point cloud shapes, enabling the generation of controllable point clouds based on user-specified shape structures and achieving state-of-the-art performance in controllable point cloud generation on the ShapeNet dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23709 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | StrucADT: Generating Structure-controlled 3D Point Clouds with Adjacency Diffusion Transformer Shu, Zhenyu Shen, Jiajun Chen, Zhongui Han, Xiaoguang Xin, Shiqing Graphics Computer Vision and Pattern Recognition Machine Learning In the field of 3D point cloud generation, numerous 3D generative models have demonstrated the ability to generate diverse and realistic 3D shapes. However, the majority of these approaches struggle to generate controllable 3D point cloud shapes that meet user-specific requirements, hindering the large-scale application of 3D point cloud generation. To address the challenge of lacking control in 3D point cloud generation, we are the first to propose controlling the generation of point clouds by shape structures that comprise part existences and part adjacency relationships. We manually annotate the adjacency relationships between the segmented parts of point cloud shapes, thereby constructing a StructureGraph representation. Based on this StructureGraph representation, we introduce StrucADT, a novel structure-controllable point cloud generation model, which consists of StructureGraphNet module to extract structure-aware latent features, cCNF Prior module to learn the distribution of the latent features controlled by the part adjacency, and Diffusion Transformer module conditioned on the latent features and part adjacency to generate structure-consistent point cloud shapes. Experimental results demonstrate that our structure-controllable 3D point cloud generation method produces high-quality and diverse point cloud shapes, enabling the generation of controllable point clouds based on user-specified shape structures and achieving state-of-the-art performance in controllable point cloud generation on the ShapeNet dataset. |
| title | StrucADT: Generating Structure-controlled 3D Point Clouds with Adjacency Diffusion Transformer |
| topic | Graphics Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2509.23709 |