Skip to main content
Springer Nature Link
Log in

SelfGeo: Self-supervised and Geodesic-Consistent Estimation of Keypoints on Deformable Shapes

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15143))

Included in the following conference series:

  • 200 Accesses

Abstract

Unsupervised 3D keypoints estimation from Point Cloud Data (PCD) is a complex task, even more challenging when an object shape is deforming. As keypoints should be semantically and geometrically consistent across all the 3D frames – each keypoint should be anchored to a specific part of the deforming shape irrespective of intrinsic and extrinsic motion. This paper presents, “SelfGeo”, a self-supervised method that computes persistent 3D keypoints of non-rigid objects from arbitrary PCDs without the need of human annotations. The gist of SelfGeo is to estimate keypoints between frames that respect invariant properties of deforming bodies. Our main contribution is to enforce that keypoints deform along with the shape while keeping constant geodesic distances among them. This principle is then propagated to the design of a set of losses which minimization let emerge repeatable keypoints in specific semantic locations of the non-rigid shape. We show experimentally that the use of geodesic has a clear advantage in challenging dynamic scenes and with different classes of deforming shapes (humans and animals). Code and data are available at: https://github.com/IIT-PAVIS/SelfGeo.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Attaiki, S., Li, L., Ovsjanikov, M.: Generalizable local feature pre-training for deformable shape analysis. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13650–13661 (2023)

    Google Scholar 

  2. Attaiki, S., Ovsjanikov, M.: NCP: neural correspondence prior for effective unsupervised shape matching. Adv. Neural. Inf. Process. Syst. 35, 28842–28857 (2022)

    Google Scholar 

  3. Bai, Y., Wang, A., Kortylewski, A., Yuille, A.: CoKe: contrastive learning for robust keypoint detection. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 65–74 (2023)

    Google Scholar 

  4. Chen, B., Abbeel, P., Pathak, D.: Unsupervised learning of visual 3D keypoints for control. In: International Conference on Machine Learning, pp. 1539–1549 (2021)

    Google Scholar 

  5. Cosmo, L., Minello, G., Bronstein, M., Rodolà, E., Rossi, L., Torsello, A.: 3D shape analysis through a quantum lens: the average mixing kernel signature. Int. J. Comput. Vision 130(6), 1474–1493 (2022)

    Article  Google Scholar 

  6. Cosmo, L., Norelli, A., Halimi, O., Kimmel, R., Rodolà, E.: LIMP: learning latent shape representations with metric preservation priors. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part III. LNCS, vol. 12348, pp. 19–35. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_2

    Chapter  Google Scholar 

  7. Dai, X., Li, S., Zhao, Q., Yang, H.: Animal pose estimation based on 3D priors. Appl. Sci. 13(3), 1466 (2023)

    Article  Google Scholar 

  8. Fernandez-Labrador, C., Chhatkuli, A., Paudel, D.P., Guerrero, J.J., Demonceaux, C., Gool, L.V.: Unsupervised learning of category-specific symmetric 3D keypoints from point sets. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 546–563. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58595-2_33

    Chapter  Google Scholar 

  9. Gupta, A., Hoffmann, P.F., Prepelitǎ, S., Robinson, P., Ithapu, V.K., Alon, D.L.: Learning to personalize equalization for high-fidelity spatial audio reproduction. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1–5. IEEE (2023)

    Google Scholar 

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

    Google Scholar 

  11. Haque, A., Peng, B., Luo, Z., Alahi, A., Yeung, S., Fei-Fei, L.: Towards viewpoint invariant 3D human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part I. LNCS, vol. 9905, pp. 160–177. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_10

    Chapter  Google Scholar 

  12. Huang, K., et al.: Skeleton-based coordinate system construction method for non-cooperative targets. Measurement 226, 114128 (2024)

    Article  Google Scholar 

  13. Jakab, T., Tucker, R., Makadia, A., Wu, J., Snavely, N., Kanazawa, A.: KeypointDeformer: unsupervised 3D keypoint discovery for shape control. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12783–12792 (2021)

    Google Scholar 

  14. Kim, S., Joo, M., Lee, J., Ko, J., Cha, J., Kim, H.J.: Semantic-aware implicit template learning via part deformation consistency. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 593–603 (2023)

    Google Scholar 

  15. Li, J., Lee, G.H.: USIP: unsupervised stable interest point detection from 3D point clouds. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 361–370 (2019)

    Google Scholar 

  16. Li, Y., Takehara, H., Taketomi, T., Zheng, B., Nießner, M.: 4DComplete: non-rigid motion estimation beyond the observable surface. In: IEEE International Conference on Computer Vision (ICCV) (2021)

    Google Scholar 

  17. Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (TOG) 34(6), 1–16 (2015)

    Article  Google Scholar 

  18. Ma, Q., et al.: Learning to dress 3D people in generative clothing. In: Computer Vision and Pattern Recognition (CVPR) (2020)

    Google Scholar 

  19. Maharjan, A., Yuan, X.: Registration of human point set using automatic key point detection and region-aware features. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 741–749 (2022)

    Google Scholar 

  20. Mohammadi, S.S., Wang, Y., Del Bue, A.: PointView-GCN: 3D shape classification with multi-view point clouds. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 3103–3107. IEEE (2021)

    Google Scholar 

  21. Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652–660 (2017)

    Google Scholar 

  22. Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, vol. 30 (2017)

    Google Scholar 

  23. Saleh, M., Wu, S.C., Cosmo, L., Navab, N., Busam, B., Tombari, F.: Bending graphs: hierarchical shape matching using gated optimal transport. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11757–11767 (2022)

    Google Scholar 

  24. Sengupta, A., Bartoli, A.: Totem NRSfM: object-wise non-rigid structure-from-motion with a topological template. Int. J. Comput. Vision 1–42 (2024)

    Google Scholar 

  25. Shi, J., Yang, H., Carlone, L.: Optimal and robust category-level perception: object pose and shape estimation from 2-D and 3-D semantic keypoints. IEEE Trans. Robot. (2023)

    Google Scholar 

  26. Shi, R., Xue, Z., You, Y., Lu, C.: Skeleton merger: an unsupervised aligned keypoint detector. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 43–52 (2021)

    Google Scholar 

  27. Su, S.Y., Yu, F., Zollhöfer, M., Rhodin, H.: A-NeRF: articulated neural radiance fields for learning human shape, appearance, and pose. Adv. Neural. Inf. Process. Syst. 34, 12278–12291 (2021)

    Google Scholar 

  28. Sun, P., et al.: Scalability in perception for autonomous driving: waymo open dataset. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446–2454 (2020)

    Google Scholar 

  29. Suwajanakorn, S., Snavely, N., Tompson, J.J., Norouzi, M.: Discovery of latent 3D keypoints via end-to-end geometric reasoning. In: Advances in Neural Information Processing Systems, vol. 31 (2018)

    Google Scholar 

  30. Tan, F., et al.: HumanGPS: geodesic preserving feature for dense human correspondences. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1820–1830 (2021)

    Google Scholar 

  31. Tang, J., Gong, Z., Yi, R., Xie, Y., Ma, L.: Lake-net: topology-aware point cloud completion by localizing aligned keypoints. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1726–1735 (2022)

    Google Scholar 

  32. Wang, Q., Kou, C., Liu, P.: Keypoint extraction of auroral arc using curvature-constrained pointNet++. In: Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition, pp. 462–467 (2022)

    Google Scholar 

  33. Weng, Z., Gorban, A.S., Ji, J., Najibi, M., Zhou, Y., Anguelov, D.: 3D human keypoints estimation from point clouds in the wild without human labels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1158–1167 (2023)

    Google Scholar 

  34. Xue, Z., Yuan, Z., Wang, J., Wang, X., Gao, Y., Xu, H.: USEEK: unsupervised SE (3)-equivariant 3D keypoints for generalizable manipulation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 1715–1722. IEEE (2023)

    Google Scholar 

  35. Yang, J., et al.: Object wake-up: 3D object rigging from a single image. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13662, pp. 311–327. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20086-1_18

    Chapter  Google Scholar 

  36. Yang, Z., Litany, O., Birdal, T., Sridhar, S., Guibas, L.: Continuous geodesic convolutions for learning on 3D shapes. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 134–144 (2021)

    Google Scholar 

  37. You, Y., Liu, W., Ze, Y., Li, Y.L., Wang, W., Lu, C.: UKPGAN: a general self-supervised keypoint detector. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 17042–17051 (2022)

    Google Scholar 

  38. You, Y., et al.: PRIN/SPRIN: on extracting point-wise rotation invariant features. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9489–9502 (2021)

    Article  Google Scholar 

  39. Yuan, H., Zhao, C., Fan, S., Jiang, J., Yang, J.: Unsupervised learning of 3D semantic keypoints with mutual reconstruction. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13662, pp. 534–549. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20086-1_31

    Chapter  Google Scholar 

  40. Zanfir, A., Zanfir, M., Gorban, A., Ji, J., Zhou, Y., Anguelov, D., Sminchisescu, C.: Hum3Dil: semi-supervised multi-modal 3D humanpose estimation for autonomous driving. In: Conference on Robot Learning, pp. 1114–1124. PMLR (2023)

    Google Scholar 

  41. Zhong, C., et al.: SNAKE: shape-aware neural 3D keypoint field. Adv. Neural. Inf. Process. Syst. 35, 7052–7064 (2022)

    Google Scholar 

  42. Zhong, C., et al.: 3D implicit transporter for temporally consistent keypoint discovery. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3869–3880 (2023)

    Google Scholar 

  43. Zhou, B., et al.: ClothesNet: an information-rich 3D garment model repository with simulated clothes environment. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 20428–20438 (2023)

    Google Scholar 

  44. Zohaib, M., Del Bue, A.: SC3K: self-supervised and coherent 3D keypoints estimation from rotated, noisy, and decimated point cloud data. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 22509–22519 (2023)

    Google Scholar 

  45. Zohaib, M., Padalkar, M.G., Morerio, P., Taiana, M., Del Bue, A.: CDHN: cross-domain hallucination network for 3D keypoints estimation. Available at SSRN 4349267 (2023)

    Google Scholar 

  46. Zohaib, M., Taiana, M., Padalkar, M.G., Del Bue, A.: 3D key-points estimation from single-view RGB images. In: Sclaroff, S., Distante, C., Leo, M., Farinella, G.M., Tombari, F. (eds.) ICIAP 2022. LNCS, vol. 13232, pp. 27–38. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-06430-2_3

    Chapter  Google Scholar 

Download references

Acknowledgements

We would like to acknowledge Pietro Morerio for fruitful discussions. This work was carried out within the frameworks of the project “RAISE - Robotics, and AI for Socio-economic Empowerment” and the PRIN 2022 project n. 2022AL45R2 (EYE-FI.AI, CUP H53D2300350-0001). This work has been supported by European Union - NextGenerationEU.

Author information

Authors and Affiliations

  1. Pattern Analysis and Computer Vision, Italian Institute of Technology, Genoa, Italy

    Mohammad Zohaib & Alessio Del Bue

  2. Ca’ Foscari University of Venice, Venice, Italy

    Luca Cosmo

Authors
  1. Mohammad Zohaib
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Luca Cosmo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Alessio Del Bue
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mohammad Zohaib .

Editor information

Editors and Affiliations

  1. University of Birmingham, Birmingham, UK

    Aleš Leonardis

  2. University of Trento, Trento, Italy

    Elisa Ricci

  3. Technical University of Darmstadt, Darmstadt, Germany

    Stefan Roth

  4. Princeton University, Princeton, NJ, USA

    Olga Russakovsky

  5. Czech Technical University in Prague, Prague, Czech Republic

    Torsten Sattler

  6. École des Ponts ParisTech, Marne-la-Vallée, France

    Gül Varol

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 53506 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 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

Zohaib, M., Cosmo, L., Del Bue, A. (2025). SelfGeo: Self-supervised and Geodesic-Consistent Estimation of Keypoints on Deformable Shapes. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15143. Springer, Cham. https://doi.org/10.1007/978-3-031-73013-9_5

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-73013-9_5

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-73012-2

  • Online ISBN: 978-3-031-73013-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation