SHREC'19: Shape correspondence with isometric and non-isometric deformations

R. M. Dyke; C. Stride; Y. K. Lai; P. L. Rosin; M. Aubry; A. Boyarski; A. M. Bronstein; M. M. Bronstein; D. Cremers; M. Fisher; T. Groueix; D. Guo; V. G. Kim; R. Kimmel; Z. Lähner; K. Li; O. Litany; E. Rodolà; B. C. Russell; Y. Sahillioglu; R. Slossberg; G. K.L. Tam; M. Vestner; Z. Wu; J. Yang

doi:10.2312/3dor.20191069

SHREC'19: Shape correspondence with isometric and non-isometric deformations

R. M. Dyke, C. Stride, Y. K. Lai, P. L. Rosin, M. Aubry, A. Boyarski, A. M. Bronstein, M. M. Bronstein, D. Cremers, M. Fisher, T. Groueix, D. Guo, V. G. Kim, R. Kimmel, Z. Lähner, K. Li, O. Litany, E. Rodolà, B. C. Russell, Y. SahilliogluR. Slossberg, G. K.L. Tam, M. Vestner, Z. Wu, J. Yang

Computer Science

Technion - Israel Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset of scanned 3D shapes undergoing various controlled deformations (articulating, bending, stretching and topologically changing), along with ground truth correspondences. With the aid of this tiered benchmark of increasingly challenging real scans, we explore this problem and investigate how robust current state-of-the-art methods perform in different challenging registration and correspondence scenarios. We discover that changes in topology is a challenging problem for some methods and that machine learning-based approaches prove to be more capable of handling non-isometric deformations on shapes that are moderately similar to the training set.

Original language	English
Title of host publication	EG 3DOR 2019 - Eurographics Workshop on 3D Object Retrieval
Editors	Dieter Fellner
Publisher	Eurographics Association
Pages	111-119
Number of pages	9
ISBN (Electronic)	9783038680772
DOIs	https://doi.org/10.2312/3dor.20191069
State	Published - 2019
Event	12th Eurographics Workshop on 3D Object Retrieval, 3DOR 2019, in conjunction with the 40th Annual Conference of the European Association for Computer Graphics, EG 2019 - Genoa, Italy Duration: 5 May 2019 → 6 May 2019

Publication series

Name	Eurographics Workshop on 3D Object Retrieval, EG 3DOR
Volume	PartF160897

Conference

Conference	12th Eurographics Workshop on 3D Object Retrieval, 3DOR 2019, in conjunction with the 40th Annual Conference of the European Association for Computer Graphics, EG 2019
Country/Territory	Italy
City	Genoa
Period	5/05/19 → 6/05/19

All Science Journal Classification (ASJC) codes

Computer Graphics and Computer-Aided Design
Computer Vision and Pattern Recognition
Human-Computer Interaction

Access to Document

10.2312/3dor.20191069

Cite this

Dyke, R. M., Stride, C., Lai, Y. K., Rosin, P. L., Aubry, M., Boyarski, A., Bronstein, A. M., Bronstein, M. M., Cremers, D., Fisher, M., Groueix, T., Guo, D., Kim, V. G., Kimmel, R., Lähner, Z., Li, K., Litany, O., Rodolà, E., Russell, B. C., ... Yang, J. (2019). SHREC'19: Shape correspondence with isometric and non-isometric deformations. In D. Fellner (Ed.), EG 3DOR 2019 - Eurographics Workshop on 3D Object Retrieval (pp. 111-119). (Eurographics Workshop on 3D Object Retrieval, EG 3DOR; Vol. PartF160897). Eurographics Association. https://doi.org/10.2312/3dor.20191069

@inproceedings{b9775510aa644990b3772fe33704ca89,

title = "SHREC'19: Shape correspondence with isometric and non-isometric deformations",

abstract = "The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset of scanned 3D shapes undergoing various controlled deformations (articulating, bending, stretching and topologically changing), along with ground truth correspondences. With the aid of this tiered benchmark of increasingly challenging real scans, we explore this problem and investigate how robust current state-of-the-art methods perform in different challenging registration and correspondence scenarios. We discover that changes in topology is a challenging problem for some methods and that machine learning-based approaches prove to be more capable of handling non-isometric deformations on shapes that are moderately similar to the training set.",

author = "Dyke, {R. M.} and C. Stride and Lai, {Y. K.} and Rosin, {P. L.} and M. Aubry and A. Boyarski and Bronstein, {A. M.} and Bronstein, {M. M.} and D. Cremers and M. Fisher and T. Groueix and D. Guo and Kim, {V. G.} and R. Kimmel and Z. L{\"a}hner and K. Li and O. Litany and E. Rodol{\`a} and Russell, {B. C.} and Y. Sahillioglu and R. Slossberg and Tam, {G. K.L.} and M. Vestner and Z. Wu and J. Yang",

note = "Publisher Copyright: {\textcopyright} 2019 The Author(s); 12th Eurographics Workshop on 3D Object Retrieval, 3DOR 2019, in conjunction with the 40th Annual Conference of the European Association for Computer Graphics, EG 2019 ; Conference date: 05-05-2019 Through 06-05-2019",

year = "2019",

doi = "10.2312/3dor.20191069",

language = "الإنجليزيّة",

series = "Eurographics Workshop on 3D Object Retrieval, EG 3DOR",

publisher = "Eurographics Association",

pages = "111--119",

editor = "Dieter Fellner",

booktitle = "EG 3DOR 2019 - Eurographics Workshop on 3D Object Retrieval",

}

Dyke, RM, Stride, C, Lai, YK, Rosin, PL, Aubry, M, Boyarski, A, Bronstein, AM, Bronstein, MM, Cremers, D, Fisher, M, Groueix, T, Guo, D, Kim, VG, Kimmel, R, Lähner, Z, Li, K, Litany, O, Rodolà, E, Russell, BC, Sahillioglu, Y, Slossberg, R, Tam, GKL, Vestner, M, Wu, Z & Yang, J 2019, SHREC'19: Shape correspondence with isometric and non-isometric deformations. in D Fellner (ed.), EG 3DOR 2019 - Eurographics Workshop on 3D Object Retrieval. Eurographics Workshop on 3D Object Retrieval, EG 3DOR, vol. PartF160897, Eurographics Association, pp. 111-119, 12th Eurographics Workshop on 3D Object Retrieval, 3DOR 2019, in conjunction with the 40th Annual Conference of the European Association for Computer Graphics, EG 2019, Genoa, Italy, 5/05/19. https://doi.org/10.2312/3dor.20191069

SHREC'19: Shape correspondence with isometric and non-isometric deformations. / Dyke, R. M.; Stride, C.; Lai, Y. K. et al.
EG 3DOR 2019 - Eurographics Workshop on 3D Object Retrieval. ed. / Dieter Fellner. Eurographics Association, 2019. p. 111-119 (Eurographics Workshop on 3D Object Retrieval, EG 3DOR; Vol. PartF160897).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - SHREC'19

T2 - 12th Eurographics Workshop on 3D Object Retrieval, 3DOR 2019, in conjunction with the 40th Annual Conference of the European Association for Computer Graphics, EG 2019

AU - Dyke, R. M.

AU - Stride, C.

AU - Lai, Y. K.

AU - Rosin, P. L.

AU - Aubry, M.

AU - Boyarski, A.

AU - Bronstein, A. M.

AU - Bronstein, M. M.

AU - Cremers, D.

AU - Fisher, M.

AU - Groueix, T.

AU - Guo, D.

AU - Kim, V. G.

AU - Kimmel, R.

AU - Lähner, Z.

AU - Li, K.

AU - Litany, O.

AU - Rodolà, E.

AU - Russell, B. C.

AU - Sahillioglu, Y.

AU - Slossberg, R.

AU - Tam, G. K.L.

AU - Vestner, M.

AU - Wu, Z.

AU - Yang, J.

PY - 2019

Y1 - 2019

N2 - The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset of scanned 3D shapes undergoing various controlled deformations (articulating, bending, stretching and topologically changing), along with ground truth correspondences. With the aid of this tiered benchmark of increasingly challenging real scans, we explore this problem and investigate how robust current state-of-the-art methods perform in different challenging registration and correspondence scenarios. We discover that changes in topology is a challenging problem for some methods and that machine learning-based approaches prove to be more capable of handling non-isometric deformations on shapes that are moderately similar to the training set.

AB - The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem. When applying such techniques to real scans, the problem is compounded by topological and geometric inconsistencies between shapes. In this paper, we capture a benchmark dataset of scanned 3D shapes undergoing various controlled deformations (articulating, bending, stretching and topologically changing), along with ground truth correspondences. With the aid of this tiered benchmark of increasingly challenging real scans, we explore this problem and investigate how robust current state-of-the-art methods perform in different challenging registration and correspondence scenarios. We discover that changes in topology is a challenging problem for some methods and that machine learning-based approaches prove to be more capable of handling non-isometric deformations on shapes that are moderately similar to the training set.

UR - http://www.scopus.com/inward/record.url?scp=85088173452&partnerID=8YFLogxK

U2 - 10.2312/3dor.20191069

DO - 10.2312/3dor.20191069

M3 - منشور من مؤتمر

T3 - Eurographics Workshop on 3D Object Retrieval, EG 3DOR

SP - 111

EP - 119

BT - EG 3DOR 2019 - Eurographics Workshop on 3D Object Retrieval

A2 - Fellner, Dieter

PB - Eurographics Association

Y2 - 5 May 2019 through 6 May 2019

ER -

SHREC'19: Shape correspondence with isometric and non-isometric deformations

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this