Skip to main content

Autoregressive 3D Shape Generation via Canonical Mapping

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13663))

Included in the following conference series:

Abstract

With the capacity of modeling long-range dependencies in sequential data, transformers have shown remarkable performances in a variety of generative tasks such as image, audio, and text generation. Yet, taming them in generating less structured and voluminous data formats such as high-resolution point clouds have seldom been explored due to ambiguous sequentialization processes and infeasible computation burden. In this paper, we aim to further exploit the power of transformers and employ them for the task of 3D point cloud generation. The key idea is to decompose point clouds of one category into semantically aligned sequences of shape compositions, via a learned canonical space. These shape compositions can then be quantized and used to learn a context-rich composition codebook for point cloud generation. Experimental results on point cloud reconstruction and unconditional generation show that our model performs favorably against state-of-the-art approaches. Furthermore, our model can be easily extended to multi-modal shape completion as an application for conditional shape generation. The source code and trained models can be found at https://github.com/AnjieCheng/CanonicalVAE.

A.-C. Cheng, X. Li and S. Liu—Equal contribution.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representations and generative models for 3D point clouds. In: ICML, pp. 40–49 (2018)

    Google Scholar 

  2. Brown, T., et al.: Language models are few-shot learners. In: NeurIPS (2020)

    Google Scholar 

  3. Cai, R., et al.: Learning gradient fields for shape generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 364–381. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_22

    Chapter  Google Scholar 

  4. Cai, Z., Ravichandran, A., Maji, S., Fowlkes, C., Tu, Z., Soatto, S.: Exponential moving average normalization for self-supervised and semi-supervised learning. In: CVPR (2021)

    Google Scholar 

  5. Chan, E.R., et al.: Efficient geometry-aware 3D generative adversarial networks. In: CVPR (2022)

    Google Scholar 

  6. Chang, A.X., et al.: Shapenet: An information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)

  7. Chen, N., et al.: Unsupervised learning of intrinsic structural representation points. In: CVPR (2020)

    Google Scholar 

  8. Cheng, A.C., Li, X., Sun, M., Yang, M.H., Liu, S.: Learning 3D dense correspondence via canonical point autoencoder. In: NeurIPS (2021)

    Google Scholar 

  9. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)

  10. Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)

  11. Engel, N., Belagiannis, V., Dietmayer, K.: Point transformer. IEEE. Access 9, 134826–134840 (2021)

    Article  Google Scholar 

  12. Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR (2021)

    Google Scholar 

  13. Gadelha, M., Wang, R., Maji, S.: Multiresolution tree networks for 3d point cloud processing. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 105–122. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_7

    Chapter  Google Scholar 

  14. Groueix, T., Fisher, M., Kim, V.G., Russell, B.C., Aubry, M.: A papier-mâché approach to learning 3D surface generation. In: CVPR, pp. 216–224 (2018)

    Google Scholar 

  15. Guo, M.H., PCT: Point cloud transformer. Comput. Vis. Media 7, 187–199 (2021)

    Google Scholar 

  16. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)

    Google Scholar 

  17. Kim, J., Yoo, J., Lee, J., Hong, S.: SetVAE: learning hierarchical composition for generative modeling of set-structured data. In: CVPR, pp. 15059–15068 (2021)

    Google Scholar 

  18. Li, R., Li, X., Hui, K.H., Fu, C.W.: SP-GAN: sphere-guided 3D shape generation and manipulation. Trans. Graph. 40(4), 1–12 (2021)

    Article  Google Scholar 

  19. Liu, M., Sheng, L., Yang, S., Shao, J., Hu, S.M.: Morphing and sampling network for dense point cloud completion. In: AAAI, pp. 11596–11603 (2020)

    Google Scholar 

  20. Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV (2021)

    Google Scholar 

  21. Luo, S., Hu, W.: Diffusion probabilistic models for 3D point cloud generation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2837–2845 (2021)

    Google Scholar 

  22. Mittal, P., Cheng, Y.C., Singh, M., Tulsiani, S.: AutoSDF: shape priors for 3D completion, reconstruction and generation. arXiv preprint arXiv:2203.09516 (2022)

  23. Razavi, A., Van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: NeurIPS, vol. 32 (2019)

    Google Scholar 

  24. Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: ICCV (2021)

    Google Scholar 

  25. Sun, Y., Wang, Y., Liu, Z., Siegel, J., Sarma, S.: PointGrow: autoregressively learned point cloud generation with self-attention. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 61–70 (2020)

    Google Scholar 

  26. Van Den Oord, A., et al.: Neural discrete representation learning. In: NeurIPS, vol. 30 (2017)

    Google Scholar 

  27. Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)

    Google Scholar 

  28. Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph cnn for learning on point clouds. Trans. Graph. 38(5), 1–12 (2019)

    Article  Google Scholar 

  29. Wu, J., Zhang, C., Xue, T., Freeman, B., Tenenbaum, J.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In: NeurIPS (2016)

    Google Scholar 

  30. Wu, R., Chen, X., Zhuang, Y., Chen, B.: Multimodal Shape completion via conditional generative adversarial networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 281–296. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58548-8_17

    Chapter  Google Scholar 

  31. Xiang, P., e al.: nowflakeNet: point cloud completion by snowflake point deconvolution with skip-transformer. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), (2021)

    Google Scholar 

  32. Yan, X., Lin, L., Mitra, N.J., Lischinski, D., Cohen-Or, D., Huang, H.: ShapeFormer: Transformer-based shape completion via sparse representation. In: CVPR, pp. 6239–6249 (2022)

    Google Scholar 

  33. Yang, G., Huang, X., Hao, Z., Liu, M.Y., Belongie, S., Hariharan, B.: PointFlow: 3D point cloud generation with continuous normalizing flows. In: CVPR, pp. 4541–4550 (2019)

    Google Scholar 

  34. Yang, Y., Feng, C., Shen, Y., Tian, D.: FoldingNet: point cloud auto-encoder via deep grid deformation. In: CVPR, pp. 206–215 (2018)

    Google Scholar 

  35. Yu, J., et al.: Vector-quantized image modeling with improved VQGAN. In: ICLR (202)

    Google Scholar 

  36. Zhang, X., Zhang, Z., Zhang, C., Tenenbaum, J.B., Freeman, W.T., Wu, J.: Learning to Reconstruct Shapes From Unseen Classes. In: NeurIPS (2018)

    Google Scholar 

  37. Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 16259–16268 (2021)

    Google Scholar 

  38. Zhou, L., Du, Y., Wu, J.: 3D shape generation and completion through point-voxel diffusion. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 5826–5835 (2021)

    Google Scholar 

Download references

Acknowledgments

The MOST, Taiwan under Grants 110-2634-F-002-051, MOST Joint Research Center for AI Technology, All Vista Healthcare, and NSF CAREER grant 1149783. We thank National Center for High-performance Computing (NCHC) for providing computational and storage resources.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to An-Chieh Cheng .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 15665 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Cheng, AC., Li, X., Liu, S., Sun, M., Yang, MH. (2022). Autoregressive 3D Shape Generation via Canonical Mapping. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13663. Springer, Cham. https://doi.org/10.1007/978-3-031-20062-5_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20062-5_6

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20061-8

  • Online ISBN: 978-3-031-20062-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics