Synonyms
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]...
References
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
Tombari F, Salti S, Di Stefano L (2010) Unique signatures of histograms for local surface description. In: ECCV
Zeng A, Song S, Nieãÿner M, Fisher M, Xiao J, Funkhouser T (2017) 3Dmatch: learning local geometric descriptors from RGB-D reconstructions. In: CVPR
Khoury M, Zhou QY, Koltun V (2017) Learning compact geometric features. In: ICCV
Deng H, Birdal T, Ilic S (2018) PPF-FoldNet: unsupervised learning of rotation invariant 3D local descriptors. In: ECCV
Deng H, Birdal T, Ilic S (2018) PPFNet: global context aware local features for robust 3D point matching. In: CVPR
Zhao Y, Birdal T, Deng H, Tombari F (2019) 3D point capsule networks. In: CVPR
Gojcic Z, Zhou C, Wegner JD, Wieser A (2019) The perfect match: 3D point cloud matching with smoothed densities. In: CVPR
Spezialetti R, Salti S, Di Stefano L (2019) Learning an effective equivariant 3D descriptor without supervision. In: ICCV
Choy C, Park J, Koltun V (2019) Fully convolutional geometric features. In: ICCV
Johnson A, Hebert M (1999) Using spin images for efficient object recognition in cluttered 3D scenes. PAMI 21(5):433–449
Frome A, Huber D, Kolluri R, Bülow T, Malik J (2004) Recognizing objects in range data using regional point descriptors. In: ECCV
Chua CS, Jarvis R (1997) Point signatures: a new representation for 3D object recognition. IJCV 25(1):63–85
Qi CR, Su H, Mo K, Guibas LJ (2017) Pointnet: deep learning on point sets for 3D classification and segmentation. In: CVPR
Yang Y, Feng C, Shen Y, Tian D (2018) Foldingnet: point cloud auto-encoder via deep grid deformation. In: CVPR
Rusu RB, Blodow N, Marton ZC, Beetz M (2008) Aligning point cloud views using persistent feature histograms. In: IROS
Rusu RB, Blodow N, Beetz M (2009) Fast point feature histograms (FPFH) for 3D registration. In: ICRA
Tombari F, Salti S, Di Stefano L (2010) Unique shape context for 3D data description. In: ACM
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
Su H, Maji S, Kalogerakis E, Learned-Miller E (2015) Multi-view convolutional neural networks for 3D shape recognition. In: ICCV
Maturana D, Scherer S (2015) VoxNet: a 3D convolutional neural network for real-time object recognition. In: IROS
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
Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: CVPR
Hadsell R, Chopra S, LeCun Y (2006) Dimensionality reduction by learning an invariant mapping. In: CVPR
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
Hermans A, Beyer L, Leibe B (2017) In defense of the triplet loss for person re-identification. arXiv
Drost B, Ulrich M, Navab N, Ilic S (2010) Model globally, match locally: efficient and robust 3D object recognition. In: CVPR
Cohen ST, Geiger M, Kohler M, Welling M (2018) Spherical CNNs. arXiv
Qi CR, Yi L, Su H, Guibas LJ (2017) Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: NIPS
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
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
Yang Y, Feng C, Shen Y, Tian D (2018) Foldingnet: point cloud auto-encoder via deep grid deformation. In: CVPR
Groueix T, Fisher M, Kim VG, Russell BC, Aubry M (2018) AtlasNet: a papier-Mâché approach to learning 3D surface generation. In: CVPR
Rethage D, Wald J, Sturm J, Navab N, Tombari F (2018) Fully-convolutional point networks for large-scale point clouds. In: ECCV
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
Author information
Authors and Affiliations
Corresponding author
Section Editor information
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this entry
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