Attention-Based Part Assembly for 3D Volumetric Shape Modeling

Chengzhi Wu, Junwei Zheng, Julius Pfrommer, Jürgen Beyerer

CVPRW 2023 pp. 2717-2726

doi:10.1109/CVPRW59228.2023.00272 /cvprw/2023/wu2023cvprw-attentionbased/

Abstract

Modeling a 3D volumetric shape as an assembly of decomposed shape parts is much more challenging, but semantically more valuable than direct reconstruction from a full shape representation. The neural network needs to implicitly learn part relations coherently, which is typically performed by dedicated network layers that can generate transformation matrices for each part. In this paper, we propose a VoxAttention network architecture for attention-based part assembly. We further propose a variant of using channel-wise part attention and show the advantages of this approach. Experimental results show that our method outperforms most state-of-the-art methods for the part relation-aware 3D shape modeling task.

PDF CVPRW Semantic Scholar

Cite

Text

Wu et al. "Attention-Based Part Assembly for 3D Volumetric Shape Modeling." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00272

Markdown

[Wu et al. "Attention-Based Part Assembly for 3D Volumetric Shape Modeling." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/wu2023cvprw-attentionbased/) doi:10.1109/CVPRW59228.2023.00272

BibTeX

@inproceedings{wu2023cvprw-attentionbased,
  title     = {{Attention-Based Part Assembly for 3D Volumetric Shape Modeling}},
  author    = {Wu, Chengzhi and Zheng, Junwei and Pfrommer, Julius and Beyerer, Jürgen},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2023},
  pages     = {2717-2726},
  doi       = {10.1109/CVPRW59228.2023.00272},
  url       = {https://mlanthology.org/cvprw/2023/wu2023cvprw-attentionbased/}
}