Shape Retrieval of Non-rigid 3D Human Models

D. Pickup; X. Sun; P. L. Rosin; R. R. Martin; Z. Cheng; Z. Lian; M. Aono; A. Ben Hamza; A. Bronstein; M. Bronstein; S. Bu; U. Castellani; S. Cheng; V. Garro; A. Giachetti; A. Godil; L. Isaia; J. Han; H. Johan; L. Lai; B. Li; C. Li; H. Li; R. Litman; X. Liu; Z. Liu; Y. Lu; L. Sun; G. Tam; A. Tatsuma; J. Ye

doi:10.1007/s11263-016-0903-8

Shape Retrieval of Non-rigid 3D Human Models

D. Pickup^*, X. Sun, P. L. Rosin, R. R. Martin, Z. Cheng, Z. Lian, M. Aono, A. Ben Hamza, A. Bronstein, M. Bronstein, S. Bu, U. Castellani, S. Cheng, V. Garro, A. Giachetti, A. Godil, L. Isaia, J. Han, H. Johan, L. LaiB. Li, C. Li, H. Li, R. Litman, X. Liu, Z. Liu, Y. Lu, L. Sun, G. Tam, A. Tatsuma, J. Ye

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. We extend our recent paper which provided a benchmark for testing non-rigid 3D shape retrieval algorithms on 3D human models. This benchmark provided a far stricter challenge than previous shape benchmarks. We have added 145 new models for use as a separate training set, in order to standardise the training data used and provide a fairer comparison. We have also included experiments with the FAUST dataset of human scans. All participants of the previous benchmark study have taken part in the new tests reported here, many providing updated results using the new data. In addition, further participants have also taken part, and we provide extra analysis of the retrieval results. A total of 25 different shape retrieval methods are compared.

Original language	English
Pages (from-to)	169-193
Number of pages	25
Journal	International Journal of Computer Vision
Volume	120
Issue number	2
DOIs	https://doi.org/10.1007/s11263-016-0903-8
State	Published - 1 Nov 2016
Externally published	Yes

Keywords

3D humans
3D shape retrieval
Benchmark
Non-rigid 3D shape retrieval

Access to Document

10.1007/s11263-016-0903-8

Cite this

Pickup, D., Sun, X., Rosin, P. L., Martin, R. R., Cheng, Z., Lian, Z., Aono, M., Hamza, A. B., Bronstein, A., Bronstein, M., Bu, S., Castellani, U., Cheng, S., Garro, V., Giachetti, A., Godil, A., Isaia, L., Han, J., Johan, H., ... Ye, J. (2016). Shape Retrieval of Non-rigid 3D Human Models. International Journal of Computer Vision, 120(2), 169-193. https://doi.org/10.1007/s11263-016-0903-8

@article{8026a44667274c7bbae38049aafcc297,

title = "Shape Retrieval of Non-rigid 3D Human Models",

abstract = "3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. We extend our recent paper which provided a benchmark for testing non-rigid 3D shape retrieval algorithms on 3D human models. This benchmark provided a far stricter challenge than previous shape benchmarks. We have added 145 new models for use as a separate training set, in order to standardise the training data used and provide a fairer comparison. We have also included experiments with the FAUST dataset of human scans. All participants of the previous benchmark study have taken part in the new tests reported here, many providing updated results using the new data. In addition, further participants have also taken part, and we provide extra analysis of the retrieval results. A total of 25 different shape retrieval methods are compared.",

keywords = "3D humans, 3D shape retrieval, Benchmark, Non-rigid 3D shape retrieval",

author = "D. Pickup and X. Sun and Rosin, {P. L.} and Martin, {R. R.} and Z. Cheng and Z. Lian and M. Aono and Hamza, {A. Ben} and A. Bronstein and M. Bronstein and S. Bu and U. Castellani and S. Cheng and V. Garro and A. Giachetti and A. Godil and L. Isaia and J. Han and H. Johan and L. Lai and B. Li and C. Li and H. Li and R. Litman and X. Liu and Z. Liu and Y. Lu and L. Sun and G. Tam and A. Tatsuma and J. Ye",

note = "Publisher Copyright: {\textcopyright} 2016, The Author(s).",

year = "2016",

month = nov,

day = "1",

doi = "10.1007/s11263-016-0903-8",

language = "אנגלית",

volume = "120",

pages = "169--193",

journal = "International Journal of Computer Vision",

issn = "0920-5691",

publisher = "Springer Netherlands",

number = "2",

}

Pickup, D, Sun, X, Rosin, PL, Martin, RR, Cheng, Z, Lian, Z, Aono, M, Hamza, AB, Bronstein, A, Bronstein, M, Bu, S, Castellani, U, Cheng, S, Garro, V, Giachetti, A, Godil, A, Isaia, L, Han, J, Johan, H, Lai, L, Li, B, Li, C, Li, H, Litman, R, Liu, X, Liu, Z, Lu, Y, Sun, L, Tam, G, Tatsuma, A & Ye, J 2016, 'Shape Retrieval of Non-rigid 3D Human Models', International Journal of Computer Vision, vol. 120, no. 2, pp. 169-193. https://doi.org/10.1007/s11263-016-0903-8

TY - JOUR

T1 - Shape Retrieval of Non-rigid 3D Human Models

AU - Pickup, D.

AU - Sun, X.

AU - Rosin, P. L.

AU - Martin, R. R.

AU - Cheng, Z.

AU - Lian, Z.

AU - Aono, M.

AU - Hamza, A. Ben

AU - Bronstein, A.

AU - Bronstein, M.

AU - Bu, S.

AU - Castellani, U.

AU - Cheng, S.

AU - Garro, V.

AU - Giachetti, A.

AU - Godil, A.

AU - Isaia, L.

AU - Han, J.

AU - Johan, H.

AU - Lai, L.

AU - Li, B.

AU - Li, C.

AU - Li, H.

AU - Litman, R.

AU - Liu, X.

AU - Liu, Z.

AU - Lu, Y.

AU - Sun, L.

AU - Tam, G.

AU - Tatsuma, A.

AU - Ye, J.

PY - 2016/11/1

Y1 - 2016/11/1

N2 - 3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. We extend our recent paper which provided a benchmark for testing non-rigid 3D shape retrieval algorithms on 3D human models. This benchmark provided a far stricter challenge than previous shape benchmarks. We have added 145 new models for use as a separate training set, in order to standardise the training data used and provide a fairer comparison. We have also included experiments with the FAUST dataset of human scans. All participants of the previous benchmark study have taken part in the new tests reported here, many providing updated results using the new data. In addition, further participants have also taken part, and we provide extra analysis of the retrieval results. A total of 25 different shape retrieval methods are compared.

AB - 3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. We extend our recent paper which provided a benchmark for testing non-rigid 3D shape retrieval algorithms on 3D human models. This benchmark provided a far stricter challenge than previous shape benchmarks. We have added 145 new models for use as a separate training set, in order to standardise the training data used and provide a fairer comparison. We have also included experiments with the FAUST dataset of human scans. All participants of the previous benchmark study have taken part in the new tests reported here, many providing updated results using the new data. In addition, further participants have also taken part, and we provide extra analysis of the retrieval results. A total of 25 different shape retrieval methods are compared.

KW - 3D humans

KW - 3D shape retrieval

KW - Benchmark

KW - Non-rigid 3D shape retrieval

UR - http://www.scopus.com/inward/record.url?scp=84983750767&partnerID=8YFLogxK

U2 - 10.1007/s11263-016-0903-8

DO - 10.1007/s11263-016-0903-8

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:84983750767

SN - 0920-5691

VL - 120

SP - 169

EP - 193

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

IS - 2

ER -

Shape Retrieval of Non-rigid 3D Human Models

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this