Computing local binary patterns on mesh manifolds for 3D texture retrieval

Naoufel Werghi; Claudio Tortorici; Stefano Berretti; Alberto Del Bimbo

doi:10.2312/3DOR.20151061

Computing local binary patterns on mesh manifolds for 3D texture retrieval

Naoufel Werghi, Claudio Tortorici, Stefano Berretti, Alberto Del Bimbo

Electrical Engineering

University of Florence

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

3 Scopus citations

Abstract

In this paper, we present and experiment a novel approach for retrieving 3D geometric texture patterns on 2D mesh-manifolds (i.e., surfaces in the 3D space) using local binary patterns (LBP) constructed on the mesh. The method is based on the recently proposed mesh-LBP framework [WBD15]. Compared to its depth-image counterpart, the mesh-LBP is distinguished by the following features: a) inherits the intrinsic advantages of mesh surface (e.g., preservation of the full geometry); b) does not require normalization; c) can accommodate partial matching. Experiments conducted with public 3D models with geometric texture showcase the superiority of the mesh-LBP descriptors in comparison with competitive methods.

Original language	British English
Title of host publication	EG 3DOR 2015 - Eurographics 2015 Workshop on 3D Object Retrieval
Editors	Michela Spagnuolo, Luc Van Gool, Ioannis Pratikakis, Theoharis Theoharis, Remco Veltkamp
Pages	91-94
Number of pages	4
ISBN (Electronic)	9783905674781
DOIs	https://doi.org/10.2312/3DOR.20151061
State	Published - 2015
Event	8th Eurographics Workshop on 3D Object Retrieval, 3DOR 2015 - Zurich, Switzerland Duration: 2 May 2015 → 3 May 2015

Publication series

Name	Eurographics Workshop on 3D Object Retrieval, EG 3DOR
ISSN (Print)	1997-0463
ISSN (Electronic)	1997-0471

Conference

Conference	8th Eurographics Workshop on 3D Object Retrieval, 3DOR 2015
Country/Territory	Switzerland
City	Zurich
Period	2/05/15 → 3/05/15

Access to Document

10.2312/3DOR.20151061

Cite this

Werghi, N., Tortorici, C., Berretti, S., & Del Bimbo, A. (2015). Computing local binary patterns on mesh manifolds for 3D texture retrieval. In M. Spagnuolo, L. Van Gool, I. Pratikakis, T. Theoharis, & R. Veltkamp (Eds.), EG 3DOR 2015 - Eurographics 2015 Workshop on 3D Object Retrieval (pp. 91-94). (Eurographics Workshop on 3D Object Retrieval, EG 3DOR). https://doi.org/10.2312/3DOR.20151061

Werghi, Naoufel ; Tortorici, Claudio ; Berretti, Stefano et al. / Computing local binary patterns on mesh manifolds for 3D texture retrieval. EG 3DOR 2015 - Eurographics 2015 Workshop on 3D Object Retrieval. editor / Michela Spagnuolo ; Luc Van Gool ; Ioannis Pratikakis ; Theoharis Theoharis ; Remco Veltkamp. 2015. pp. 91-94 (Eurographics Workshop on 3D Object Retrieval, EG 3DOR).

@inproceedings{81d090a60b054bdda094dcb313774a65,

title = "Computing local binary patterns on mesh manifolds for 3D texture retrieval",

abstract = "In this paper, we present and experiment a novel approach for retrieving 3D geometric texture patterns on 2D mesh-manifolds (i.e., surfaces in the 3D space) using local binary patterns (LBP) constructed on the mesh. The method is based on the recently proposed mesh-LBP framework [WBD15]. Compared to its depth-image counterpart, the mesh-LBP is distinguished by the following features: a) inherits the intrinsic advantages of mesh surface (e.g., preservation of the full geometry); b) does not require normalization; c) can accommodate partial matching. Experiments conducted with public 3D models with geometric texture showcase the superiority of the mesh-LBP descriptors in comparison with competitive methods.",

author = "Naoufel Werghi and Claudio Tortorici and Stefano Berretti and {Del Bimbo}, Alberto",

note = "Publisher Copyright: {\textcopyright} The Eurographics Association 2015.; 8th Eurographics Workshop on 3D Object Retrieval, 3DOR 2015 ; Conference date: 02-05-2015 Through 03-05-2015",

year = "2015",

doi = "10.2312/3DOR.20151061",

language = "British English",

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

pages = "91--94",

editor = "Michela Spagnuolo and {Van Gool}, Luc and Ioannis Pratikakis and Theoharis Theoharis and Remco Veltkamp",

booktitle = "EG 3DOR 2015 - Eurographics 2015 Workshop on 3D Object Retrieval",

}

Werghi, N, Tortorici, C, Berretti, S & Del Bimbo, A 2015, Computing local binary patterns on mesh manifolds for 3D texture retrieval. in M Spagnuolo, L Van Gool, I Pratikakis, T Theoharis & R Veltkamp (eds), EG 3DOR 2015 - Eurographics 2015 Workshop on 3D Object Retrieval. Eurographics Workshop on 3D Object Retrieval, EG 3DOR, pp. 91-94, 8th Eurographics Workshop on 3D Object Retrieval, 3DOR 2015, Zurich, Switzerland, 2/05/15. https://doi.org/10.2312/3DOR.20151061

Computing local binary patterns on mesh manifolds for 3D texture retrieval. / Werghi, Naoufel; Tortorici, Claudio; Berretti, Stefano et al.
EG 3DOR 2015 - Eurographics 2015 Workshop on 3D Object Retrieval. ed. / Michela Spagnuolo; Luc Van Gool; Ioannis Pratikakis; Theoharis Theoharis; Remco Veltkamp. 2015. p. 91-94 (Eurographics Workshop on 3D Object Retrieval, EG 3DOR).

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

TY - GEN

T1 - Computing local binary patterns on mesh manifolds for 3D texture retrieval

AU - Werghi, Naoufel

AU - Tortorici, Claudio

AU - Berretti, Stefano

AU - Del Bimbo, Alberto

N1 - Publisher Copyright: © The Eurographics Association 2015.

PY - 2015

Y1 - 2015

N2 - In this paper, we present and experiment a novel approach for retrieving 3D geometric texture patterns on 2D mesh-manifolds (i.e., surfaces in the 3D space) using local binary patterns (LBP) constructed on the mesh. The method is based on the recently proposed mesh-LBP framework [WBD15]. Compared to its depth-image counterpart, the mesh-LBP is distinguished by the following features: a) inherits the intrinsic advantages of mesh surface (e.g., preservation of the full geometry); b) does not require normalization; c) can accommodate partial matching. Experiments conducted with public 3D models with geometric texture showcase the superiority of the mesh-LBP descriptors in comparison with competitive methods.

AB - In this paper, we present and experiment a novel approach for retrieving 3D geometric texture patterns on 2D mesh-manifolds (i.e., surfaces in the 3D space) using local binary patterns (LBP) constructed on the mesh. The method is based on the recently proposed mesh-LBP framework [WBD15]. Compared to its depth-image counterpart, the mesh-LBP is distinguished by the following features: a) inherits the intrinsic advantages of mesh surface (e.g., preservation of the full geometry); b) does not require normalization; c) can accommodate partial matching. Experiments conducted with public 3D models with geometric texture showcase the superiority of the mesh-LBP descriptors in comparison with competitive methods.

UR - http://www.scopus.com/inward/record.url?scp=85018167062&partnerID=8YFLogxK

U2 - 10.2312/3DOR.20151061

DO - 10.2312/3DOR.20151061

M3 - Conference contribution

AN - SCOPUS:85018167062

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

SP - 91

EP - 94

BT - EG 3DOR 2015 - Eurographics 2015 Workshop on 3D Object Retrieval

A2 - Spagnuolo, Michela

A2 - Van Gool, Luc

A2 - Pratikakis, Ioannis

A2 - Theoharis, Theoharis

A2 - Veltkamp, Remco

T2 - 8th Eurographics Workshop on 3D Object Retrieval, 3DOR 2015

Y2 - 2 May 2015 through 3 May 2015

ER -

Computing local binary patterns on mesh manifolds for 3D texture retrieval

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this