Skip to main content
SpringerLink
Log in

Three-Dimensional Shape Descriptor

  • Living reference work entry
  • First Online:
Computer Vision

  • 57 Accesses

Synonyms

3D descriptor; 3D feature; Embedding

Related Concepts

Definition

A 3D shape descriptor is a compressed representation of the geometry of a surface. The estimation of a descriptor can be applied to a single point, considering only the points belonging to its neighborhood, or to the entire object involving all points of the surface.

Background

The estimation of similarities between surfaces represents the cornerstone of most 3D computer vision applications. A typical way of solving surface matching is to establish point-to-point, or shape-to-shape, correspondences obtained by matching local or global descriptors. Several metrics can be used to compare them, the most common arguably being the Euclidean distance in the descriptor space. Designing an effective descriptor is far from being an easy task. Their fundamental role has, over the years, fuelled intense activity in this field. According to [1]...

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

Access this chapter

Log in via an institution

Institutional subscriptions

References

  1. Guo Y, Bennamoun M, Sohel F, Lu M, Wan J, Kwok NM (2016) A comprehensive performance evaluation of 3D local feature descriptors. IJCV 116(1):66–89

    Article  MathSciNet  Google Scholar 

  2. Tombari F, Salti S, Di Stefano L (2010) Unique signatures of histograms for local surface description. In: ECCV

    Book  Google Scholar 

  3. Zeng A, Song S, Nieãÿner M, Fisher M, Xiao J, Funkhouser T (2017) 3Dmatch: learning local geometric descriptors from RGB-D reconstructions. In: CVPR

    Google Scholar 

  4. Khoury M, Zhou QY, Koltun V (2017) Learning compact geometric features. In: ICCV

    Book  Google Scholar 

  5. Deng H, Birdal T, Ilic S (2018) PPF-FoldNet: unsupervised learning of rotation invariant 3D local descriptors. In: ECCV

    Google Scholar 

  6. Deng H, Birdal T, Ilic S (2018) PPFNet: global context aware local features for robust 3D point matching. In: CVPR

    Google Scholar 

  7. Zhao Y, Birdal T, Deng H, Tombari F (2019) 3D point capsule networks. In: CVPR

    Book  Google Scholar 

  8. Gojcic Z, Zhou C, Wegner JD, Wieser A (2019) The perfect match: 3D point cloud matching with smoothed densities. In: CVPR

    Google Scholar 

  9. Spezialetti R, Salti S, Di Stefano L (2019) Learning an effective equivariant 3D descriptor without supervision. In: ICCV

    Book  Google Scholar 

  10. Choy C, Park J, Koltun V (2019) Fully convolutional geometric features. In: ICCV

    Book  Google Scholar 

  11. Johnson A, Hebert M (1999) Using spin images for efficient object recognition in cluttered 3D scenes. PAMI 21(5):433–449

    Article  Google Scholar 

  12. Frome A, Huber D, Kolluri R, Bülow T, Malik J (2004) Recognizing objects in range data using regional point descriptors. In: ECCV

    Book  Google Scholar 

  13. Chua CS, Jarvis R (1997) Point signatures: a new representation for 3D object recognition. IJCV 25(1):63–85

    Article  Google Scholar 

  14. Qi CR, Su H, Mo K, Guibas LJ (2017) Pointnet: deep learning on point sets for 3D classification and segmentation. In: CVPR

    Google Scholar 

  15. Yang Y, Feng C, Shen Y, Tian D (2018) Foldingnet: point cloud auto-encoder via deep grid deformation. In: CVPR

    Google Scholar 

  16. Rusu RB, Blodow N, Marton ZC, Beetz M (2008) Aligning point cloud views using persistent feature histograms. In: IROS

    Book  Google Scholar 

  17. Rusu RB, Blodow N, Beetz M (2009) Fast point feature histograms (FPFH) for 3D registration. In: ICRA

    Book  Google Scholar 

  18. Tombari F, Salti S, Di Stefano L (2010) Unique shape context for 3D data description. In: ACM

    Book  Google Scholar 

  19. Guo Y, Sohel F, Bennamoun M, Lu M, Wan J (2013) Rotational projection statistics for 3D local surface description and object recognition. IJCV 105(1): 63–86

    Article  MathSciNet  Google Scholar 

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

    Book  Google Scholar 

  21. Maturana D, Scherer S (2015) VoxNet: a 3D convolutional neural network for real-time object recognition. In: IROS

    Google Scholar 

  22. Bronstein MM, Bruna J, LeCun Y, Szlam A, Vandergheynst P (2017) Geometric deep learning: going beyond euclidean data. IEEE Signal Process Mag 34(4):18–42

    Article  Google Scholar 

  23. Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: CVPR

    Google Scholar 

  24. Hadsell R, Chopra S, LeCun Y (2006) Dimensionality reduction by learning an invariant mapping. In: CVPR

    Book  Google Scholar 

  25. Newcombe RA, Izadi S, Hilliges O, Molyneaux D, Kim D, Davison AJ, ..., Fitzgibbon AW (2011) Kinectfusion: real-time dense surface mapping and tracking. In: ISMAR

    Google Scholar 

  26. Hermans A, Beyer L, Leibe B (2017) In defense of the triplet loss for person re-identification. arXiv

    Google Scholar 

  27. Drost B, Ulrich M, Navab N, Ilic S (2010) Model globally, match locally: efficient and robust 3D object recognition. In: CVPR

    Google Scholar 

  28. Cohen ST, Geiger M, Kohler M, Welling M (2018) Spherical CNNs. arXiv

    Google Scholar 

  29. Qi CR, Yi L, Su H, Guibas LJ (2017) Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: NIPS

    Google Scholar 

  30. Yi L, Kim VG, Ceylan D, Shen I, Yan M, Su H, ..., Guibas L (2016) A scalable active framework for region annotation in 3D shape collections. ACM Trans Graph (TOG) 35(6):210

    Google Scholar 

  31. Armeni I, Sener O, Zamir AR, Jiang H, Brilakis I, Fischer M, Savarese S (2016) 3D semantic parsing of large-scale indoor spaces. In: CVPR

    Book  Google Scholar 

  32. Yang Y, Feng C, Shen Y, Tian D (2018) Foldingnet: point cloud auto-encoder via deep grid deformation. In: CVPR

    Google Scholar 

  33. Groueix T, Fisher M, Kim VG, Russell BC, Aubry M (2018) AtlasNet: a papier-Mâché approach to learning 3D surface generation. In: CVPR

    Google Scholar 

  34. Rethage D, Wald J, Sturm J, Navab N, Tombari F (2018) Fully-convolutional point networks for large-scale point clouds. In: ECCV

    Book  Google Scholar 

  35. Wu Z, Song S, Khosla A, Yu F, Zhang L, Tang X, Xiao J (2015) 3D shapenets: a deep representation for volumetric shapes. In: CVPR

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering (DISI), University of Bologna, Bologna, Italy

    Riccardo Spezialetti

  2. Google Inc., Technische Universität München, Garching b. München, Germany

    Federico Tombari

Authors
  1. Riccardo Spezialetti
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Federico Tombari
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Riccardo Spezialetti .

Section Editor information

  1. KTH Royal Institute of Technology, Stockholm, Sweden

    Atsuto Maki

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this entry

Check for updates. Verify currency and authenticity via CrossMark

Cite this entry

Spezialetti, R., Tombari, F. (2021). Three-Dimensional Shape Descriptor. In: Computer Vision. Springer, Cham. https://doi.org/10.1007/978-3-030-03243-2_423-1

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-03243-2_423-1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-03243-2

  • Online ISBN: 978-3-030-03243-2

  • eBook Packages: Springer Reference Computer SciencesReference Module Computer Science and Engineering

Publish with us

Policies and ethics

Search

Navigation