Skip to main content

MvDeCor: Multi-view Dense Correspondence Learning for Fine-Grained 3D Segmentation

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13662))

Included in the following conference series:

Abstract

We propose to utilize self-supervised techniques in the 2D domain for fine-grained 3D shape segmentation tasks. This is inspired by the observation that view-based surface representations are more effective at modeling high-resolution surface details and texture than their 3D counterparts based on point clouds or voxel occupancy. Specifically, given a 3D shape, we render it from multiple views, and set up a dense correspondence learning task within the contrastive learning framework. As a result, the learned 2D representations are view-invariant and geometrically consistent, leading to better generalization when trained on a limited number of labeled shapes than alternatives based on self-supervision in 2D or 3D alone. Experiments on textured (RenderPeople) and untextured (PartNet) 3D datasets show that our method outperforms state-of-the-art alternatives in fine-grained part segmentation. The improvements over baselines are greater when only a sparse set of views is available for training or when shapes are textured, indicating that MvDeCor benefits from both 2D processing and 3D geometric reasoning. Project page: https://nv-tlabs.github.io/MvDeCor/.

G. Sharma—The work was mainly done during Gopal’s internship at NVIDIA.

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

Similar content being viewed by others

References

  1. Renderpeople. https://renderpeople.com/

  2. Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.J.: Learning representations and generative models for 3D point clouds. In: International Conference on Machine Learning (2018)

    Google Scholar 

  3. Alliegro, A., Boscaini, D., Tommasi, T.: Joint supervised and self-supervised learning for 3D real world challenges. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 6718–6725. IEEE Computer Society (2021)

    Google Scholar 

  4. Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: ECCV (2018)

    Google Scholar 

  5. Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607 (2020)

    Google Scholar 

  6. Chen, Z., Yin, K., Fisher, M., Chaudhuri, S., Zhang, H.: BAE-NET: branched autoencoder for shape co-segmentation. In: International Conference on Computer Vision (ICCV), pp. 8490–8499 (2019)

    Google Scholar 

  7. Choy, C., Gwak, J., Savarese, S.: 4D spatio-temporal ConvNets: minkowski convolutional neural networks. In: Computer Vision and Pattern Recognition (CVPR), pp. 3075–3084 (2019)

    Google Scholar 

  8. Choy, C.B., Gwak, J., Savarese, S., Chandraker, M.: Universal correspondence network. In: Advances in Neural Information Processing Systems, vol. 30 (2016)

    Google Scholar 

  9. Gadelha, M., et al.: Label-efficient learning on point clouds using approximate convex decompositions. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 473–491. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58607-2_28

    Chapter  Google Scholar 

  10. Gadelha, M., Wang, R., Maji, S.: Multiresolution tree networks for 3D point cloud processing. In: ECCV (2018)

    Google Scholar 

  11. Genova, K., et al.: Learning 3D semantic segmentation with only 2D image supervision. In: International Conference on 3D Vision (3DV), pp. 361–372. IEEE (2021)

    Google Scholar 

  12. Ginzburg, D., Raviv, D.: Cyclic functional mapping: self-supervised correspondence between non-isometric deformable shapes. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 36–52. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58558-7_3

    Chapter  Google Scholar 

  13. Goyal, A., Law, H., Liu, B., Newell, A., Deng, J.: Revisiting point cloud shape classification with a simple and effective baseline. In: International Conference on Machine Learning (2021)

    Google Scholar 

  14. Grill, J.B., et al.: Bootstrap your own latent - a new approach to self-supervised learning. In: Advances in Neural Information Processing Systems, vol. 33 (2020)

    Google Scholar 

  15. Groueix, T., Fisher, M., Kim, V.G., Russell, B., Aubry, M.: AtlasNet: a papier-Mâché approach to learning 3D surface generation. In: Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  16. Halimi, O., Litany, O., Rodola, E., Bronstein, A.M., Kimmel, R.: Unsupervised learning of dense shape correspondence. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4370–4379 (2019)

    Google Scholar 

  17. Hamdi, A., Giancola, S., Ghanem, B.: MVTN: multi-view transformation network for 3D shape recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1–11 (2021)

    Google Scholar 

  18. Hassani, K., Haley, M.: Unsupervised multi-task feature learning on point clouds. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8160–8171 (2019)

    Google Scholar 

  19. He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9726–9735 (2020). https://doi.org/10.1109/CVPR42600.2020.00975

  20. Hou, J., Graham, B., Nießner, M., Xie, S.: Exploring data-efficient 3D scene understanding with contrastive scene contexts. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15587–15597 (2021)

    Google Scholar 

  21. Hou, J., Xie, S., Graham, B., Dai, A., Nießner, M.: Pri3d: can 3D priors help 2D representation learning? In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 5673–5682 (2021). https://doi.org/10.1109/ICCV48922.2021.00564

  22. Huang, H., Kalogerakis, E., Chaudhuri, S., Ceylan, D., Kim, V.G., Yumer, E.: Learning local shape descriptors from part correspondences with multiview convolutional networks. ACM Trans. Graph. 37(1), 1–14 (2018)

    Google Scholar 

  23. Kalogerakis, E., Averkiou, M., Maji, S., Chaudhuri, S.: 3D shape segmentation with projective convolutional networks. In: Proceedings of CVPR (2017)

    Google Scholar 

  24. Kawana, Y., Mukuta, Y., Harada, T.: Neural star domain as primitive representation. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS 2020. Curran Associates Inc., Red Hook (2020)

    Google Scholar 

  25. Kundu, A., et al.: Virtual multi-view fusion for 3D semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 518–535. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58586-0_31

    Chapter  Google Scholar 

  26. Lien, J.M., Amato, N.M.: Approximate convex decomposition of polyhedra. In: ACM Symposium on Solid and Physical Modeling (2007)

    Google Scholar 

  27. Luo, W., Schwing, A.G., Urtasun, R.: Efficient deep learning for stereo matching. In: Computer Vision and Pattern Recognition (CVPR), pp. 5695–5703 (2016)

    Google Scholar 

  28. Mo, K., et al.: Partnet: a large-scale benchmark for fine-grained and hierarchical part-level 3D object understanding. In: Computer Vision and Pattern Recognition (CVPR) (2019)

    Google Scholar 

  29. Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)

  30. Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of CVPR (2017)

    Google Scholar 

  31. Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: CVPR (2020)

    Google Scholar 

  32. Sauder, J., Sievers, B.: Self-supervised deep learning on point clouds by reconstructing space. In: Advances in Neural Information Processing Systems, pp. 12942–12952 (2019)

    Google Scholar 

  33. Sharma, G., et al.: PriFit: learning to fit primitives improves few shot point cloud segmentation. In: Computer Graphics Forum (2022). https://doi.org/10.1111/cgf.14601

  34. Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.G.: Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings of ICCV (2015)

    Google Scholar 

  35. Su, J.C., Gadelha, M., Wang, R., Maji, S.: A deeper look at 3D shape classifiers. In: European Conference on Computer Vision Workshops (ECCV) (2018)

    Google Scholar 

  36. Tulsiani, S., Su, H., Guibas, L.J., Efros, A.A., Malik, J.: Learning shape abstractions by assembling volumetric primitives. In: Computer Vision and Pattern Regognition (CVPR) (2017)

    Google Scholar 

  37. Wang, L., Li, X., Fang, Y.: Few-shot learning of part-specific probability space for 3D shape segmentation. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4504–4513 (2020)

    Google Scholar 

  38. Wang, P.S., Yang, Y.Q., Zou, Q.F., Wu, Z., Liu, Y., Tong, X.: Unsupervised 3D learning for shape analysis via multiresolution instance discrimination (2021)

    Google Scholar 

  39. Wang, X., Zhang, R., Shen, C., Kong, T., Li, L.: Dense contrastive learning for self-supervised visual pre-training. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)

    Google Scholar 

  40. Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3733–3742 (2018)

    Google Scholar 

  41. Xie, S., Gu, J., Guo, D., Qi, C.R., Guibas, L., Litany, O.: PointContrast: unsupervised pre-training for 3D point cloud understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 574–591. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_34

    Chapter  Google Scholar 

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

    Google Scholar 

  43. Yi, L., et al.: A scalable active framework for region annotation in 3D shape collections. ACM Trans. Graph. 35(6), 1–12 (2016)

    Article  Google Scholar 

  44. Zhang, Z., Girdhar, R., Joulin, A., Misra, I.: Self-supervised pretraining of 3D features on any point-cloud. In: International Conference on Computer Vision (ICCV), pp. 10252–10263 (2021)

    Google Scholar 

  45. Zhi, S., Laidlow, T., Leutenegger, S., Davison, A.J.: In-place scene labelling and understanding with implicit scene representation. In: International Conference on Computer Vision (ICCV), pp. 15838–15847 (2021)

    Google Scholar 

Download references

Acknowledgements.

Subhransu Maji acknowledges support from NSF grants #1749833 and #1908669.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Kangxue Yin .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 3927 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

Sharma, G., Yin, K., Maji, S., Kalogerakis, E., Litany, O., Fidler, S. (2022). MvDeCor: Multi-view Dense Correspondence Learning for Fine-Grained 3D Segmentation. 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 13662. Springer, Cham. https://doi.org/10.1007/978-3-031-20086-1_32

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20086-1_32

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20085-4

  • Online ISBN: 978-3-031-20086-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics