Generating implicit object fragment datasets for machine learning

One of the primary challenges inherent in utilizing deep learning models is the scarcity and accessibility hurdles associated with acquiring datasets of sufficient size to facilitate effective training of these networks. This is particularly significant in object detection, shape completion, and fra...

Full description

Saved in:
Bibliographic Details
Published in:Computers & graphics Vol. 125; p. 104104
Main Authors: López, Alfonso, Rueda, Antonio J., Segura, Rafael J., Ogayar, Carlos J., Navarro, Pablo, Fuertes, José M.
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.12.2024
Subjects:
ISSN:0097-8493
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract One of the primary challenges inherent in utilizing deep learning models is the scarcity and accessibility hurdles associated with acquiring datasets of sufficient size to facilitate effective training of these networks. This is particularly significant in object detection, shape completion, and fracture assembly. Instead of scanning a large number of real-world fragments, it is possible to generate massive datasets with synthetic pieces. However, realistic fragmentation is computationally intensive in the preparation (e.g., pre-factured models) and generation. Otherwise, simpler algorithms such as Voronoi diagrams provide faster processing speeds at the expense of compromising realism. In this context, it is required to balance computational efficiency and realism. This paper introduces a GPU-based framework for the massive generation of voxelized fragments derived from high-resolution 3D models, specifically prepared for their utilization as training sets for machine learning models. This rapid pipeline enables controlling how many pieces are produced, their dispersion and the appearance of subtle effects such as erosion. We have tested our pipeline with an archaeological dataset, producing more than 1M fragmented pieces from 1,052 Iberian vessels (Github). Although this work primarily intends to provide pieces as implicit data represented by voxels, triangle meshes and point clouds can also be inferred from the initial implicit representation. To underscore the unparalleled benefits of CPU and GPU acceleration in generating vast datasets, we compared against a realistic fragment generator that highlights the potential of our approach, both in terms of applicability and processing time. We also demonstrate the synergies between our pipeline and realistic simulators, which frequently cannot select the number and size of resulting pieces. To this end, a deep learning model was trained over realistic fragments and our dataset, showing similar results. [Display omitted] •GPU-based fragmentation of voxelized artefacts for simulating brittle fractures.•Generation of large datasets for training machine learning models.•Definition of how many fragments are produced, their dispersion and appearance.•Publication of a dataset comprising more than 1M fragments.
AbstractList One of the primary challenges inherent in utilizing deep learning models is the scarcity and accessibility hurdles associated with acquiring datasets of sufficient size to facilitate effective training of these networks. This is particularly significant in object detection, shape completion, and fracture assembly. Instead of scanning a large number of real-world fragments, it is possible to generate massive datasets with synthetic pieces. However, realistic fragmentation is computationally intensive in the preparation (e.g., pre-factured models) and generation. Otherwise, simpler algorithms such as Voronoi diagrams provide faster processing speeds at the expense of compromising realism. In this context, it is required to balance computational efficiency and realism. This paper introduces a GPU-based framework for the massive generation of voxelized fragments derived from high-resolution 3D models, specifically prepared for their utilization as training sets for machine learning models. This rapid pipeline enables controlling how many pieces are produced, their dispersion and the appearance of subtle effects such as erosion. We have tested our pipeline with an archaeological dataset, producing more than 1M fragmented pieces from 1,052 Iberian vessels (Github). Although this work primarily intends to provide pieces as implicit data represented by voxels, triangle meshes and point clouds can also be inferred from the initial implicit representation. To underscore the unparalleled benefits of CPU and GPU acceleration in generating vast datasets, we compared against a realistic fragment generator that highlights the potential of our approach, both in terms of applicability and processing time. We also demonstrate the synergies between our pipeline and realistic simulators, which frequently cannot select the number and size of resulting pieces. To this end, a deep learning model was trained over realistic fragments and our dataset, showing similar results. [Display omitted] •GPU-based fragmentation of voxelized artefacts for simulating brittle fractures.•Generation of large datasets for training machine learning models.•Definition of how many fragments are produced, their dispersion and appearance.•Publication of a dataset comprising more than 1M fragments.
ArticleNumber 104104
Author López, Alfonso
Segura, Rafael J.
Navarro, Pablo
Ogayar, Carlos J.
Fuertes, José M.
Rueda, Antonio J.
Author_xml – sequence: 1
  givenname: Alfonso
  orcidid: 0000-0003-1423-9496
  surname: López
  fullname: López, Alfonso
  email: allopezr@ujaen.es
  organization: Department of Computer Science, Campus Las Lagunillas s/n, Jaén, 23071, Spain
– sequence: 2
  givenname: Antonio J.
  orcidid: 0000-0001-7692-454X
  surname: Rueda
  fullname: Rueda, Antonio J.
  email: ajrueda@ujaen.es
  organization: Department of Computer Science, Campus Las Lagunillas s/n, Jaén, 23071, Spain
– sequence: 3
  givenname: Rafael J.
  orcidid: 0000-0002-3075-6963
  surname: Segura
  fullname: Segura, Rafael J.
  email: rsegura@ujaen.es
  organization: Department of Computer Science, Campus Las Lagunillas s/n, Jaén, 23071, Spain
– sequence: 4
  givenname: Carlos J.
  orcidid: 0000-0003-0958-990X
  surname: Ogayar
  fullname: Ogayar, Carlos J.
  email: cogayar@ujaen.es
  organization: Department of Computer Science, Campus Las Lagunillas s/n, Jaén, 23071, Spain
– sequence: 5
  givenname: Pablo
  orcidid: 0000-0003-2180-449X
  surname: Navarro
  fullname: Navarro, Pablo
  email: pnavarro@cenpat-conicet.gob.ar
  organization: Instituto Patagónico de Ciencias Sociales y Humanas, Centro Nacional Patagónico, CONICET, Puerto Madryn, Argentina
– sequence: 6
  givenname: José M.
  orcidid: 0000-0001-6624-4102
  surname: Fuertes
  fullname: Fuertes, José M.
  email: jmf@ujaen.es
  organization: Department of Computer Science, Campus Las Lagunillas s/n, Jaén, 23071, Spain
BookMark eNp9kMFKAzEQQHOoYFv9AG_5ga3ZZLdp8FSKVqHgRc9hNpnULLvZkgTBvzelnjwUhhmG4Q3zZkFmYQpIyEPNVjWr14_9ysBxxRlvSt-UmJE5Y0pWm0aJW7JIqWeMcb5u5mS7x4ARsg9H6sfT4I3PdOp6NJm6CMcRQ6YWMiTMibop0hHMlw9IB4QYCnZHbhwMCe__6pJ8vjx_7F6rw_v-bbc9VIYrmStUTYtKNA6hNVZyYbFDyY0SCB1rmHTClFGNXQsttwyk3ZQEUhgHrFNiSeRlr4lTShGdLqeWw6eQI_hB10yf7XWvi70-2-uLfSHrf-Qp-hHiz1Xm6cJgUfr2GHUyHoNB62P5jbaTv0L_AoRMd7c
CitedBy_id crossref_primary_10_1016_j_cag_2024_104145
Cites_doi 10.1016/S0305-4403(87)80008-0
10.1016/j.culher.2008.07.012
10.24963/ijcai.2023/647
10.1145/2461912.2461934
10.1007/s11263-018-1126-y
10.1145/2897824.2925902
10.1111/cgf.13953
10.1016/j.cag.2014.08.006
10.1145/3522573
10.1016/j.cag.2023.05.003
10.1145/566654.566579
10.1109/TVCG.2020.2981565
10.1109/ICCV.2019.00939
10.1111/cgf.14603
10.1109/ACCESS.2020.2965624
10.1007/s10852-008-9097-6
10.1109/CVPR52729.2023.00433
10.1007/s11042-016-4076-9
10.1109/ICCV48922.2021.00644
10.1002/cav.1443
10.1016/j.gmod.2017.06.004
10.1145/3549540
ContentType Journal Article
Copyright 2024 The Author(s)
Copyright_xml – notice: 2024 The Author(s)
DBID 6I.
AAFTH
AAYXX
CITATION
DOI 10.1016/j.cag.2024.104104
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID 10_1016_j_cag_2024_104104
S0097849324002395
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
1B1
1~.
1~5
29F
4.4
457
4G.
5GY
5VS
6I.
6TJ
7-5
71M
8P~
9JN
AAEDT
AAEDW
AAFTH
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AATTM
AAXKI
AAXUO
AAYFN
AAYWO
ABAOU
ABBOA
ABDPE
ABEFU
ABJNI
ABMAC
ABWVN
ABXDB
ACDAQ
ACGFS
ACLOT
ACNNM
ACRLP
ACRPL
ACZNC
ADBBV
ADEZE
ADGUI
ADJOM
ADMUD
ADNMO
AEBSH
AEIPS
AEKER
AFFNX
AFJKZ
AFTJW
AGHFR
AGQPQ
AGSOS
AGUBO
AGYEJ
AHHHB
AHZHX
AI.
AIALX
AIEXJ
AIGVJ
AIIUN
AIKHN
AITUG
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
APXCP
ARUGR
ASPBG
AVWKF
AXJTR
AZFZN
BKOJK
BLXMC
CS3
EBS
EFJIC
EFKBS
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
H~9
IHE
J1W
K-O
KOM
LG9
M41
MHUIS
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
PC.
Q38
R2-
ROL
RPZ
SBC
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSV
SSW
SSZ
T5K
TN5
UHS
VH1
VOH
WH7
WUQ
XPP
ZMT
ZY4
~02
~G-
~HD
9DU
AAYXX
CITATION
ID FETCH-LOGICAL-c297t-e945e934fea5cd723debe72c93eab0407f3cea51eb5a52d0a7d80a7a73cfa0b93
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001403099000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0097-8493
IngestDate Sat Nov 29 05:33:30 EST 2025
Tue Nov 18 22:25:14 EST 2025
Thu Nov 13 04:40:24 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords GPU programming
Fracture dataset
Voxel
Voronoi
Fragmentation
Language English
License This is an open access article under the CC BY-NC-ND license.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c297t-e945e934fea5cd723debe72c93eab0407f3cea51eb5a52d0a7d80a7a73cfa0b93
ORCID 0000-0001-6624-4102
0000-0003-2180-449X
0000-0001-7692-454X
0000-0003-1423-9496
0000-0002-3075-6963
0000-0003-0958-990X
OpenAccessLink https://dx.doi.org/10.1016/j.cag.2024.104104
ParticipantIDs crossref_citationtrail_10_1016_j_cag_2024_104104
crossref_primary_10_1016_j_cag_2024_104104
elsevier_sciencedirect_doi_10_1016_j_cag_2024_104104
PublicationCentury 2000
PublicationDate December 2024
2024-12-00
PublicationDateYYYYMMDD 2024-12-01
PublicationDate_xml – month: 12
  year: 2024
  text: December 2024
PublicationDecade 2020
PublicationTitle Computers & graphics
PublicationYear 2024
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Gregor, Bauer, Sipiran, Perakis, Schreck (b14) 2015
Deng, Jiang, Chen, Zhang, Yao, Song, Sun, Yang, Yan, Huang, Bajaj (b20) 2023; 113
Behley J, Garbade M, Milioto A, Quenzel J, Behnke S, Stachniss C, Gall J. SemanticKITTI: A dataset for semantic scene understanding of lidar sequences. In: 2019 IEEE/CVF international conference on computer vision (ICCV). 2019, p. 9296–306.
Lucena, Fuertes, Martínez-Carrillo, Ruiz, Carrascosa (b3) 2017; 76
URL . ISSN: 1045-0823.
Graciano, Rueda, Pospíšil, Bittner, Benes (b40) 2021; 27
Fan, Chitalu, Komura (b7) 2022; 41
Müller, Chentanez, Kim (b10) 2013; 32
Lamb, Banerjee, Banerjee (b13) 2022; 41
URL . Conference Name: 2021 IEEE/CVF International Conference on Computer Vision (ICCV) ISBN: 9781665428125 Place: Montreal, QC, Canada Publisher: IEEE.
Cheng Y-C, Lee H-Y, Tulyakov S, Schwing AG, Gui L-Y. SDFusion: Multimodal 3D shape completion, reconstruction, and generation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023, p. 4456–65, URL.
Muguercia, Bosch, Patow (b1) 2014; 45
Skibo, Schiffer (b37) 1987; 14
Ogayar-Anguita, Rueda-Ruiz, Segura-Sánchez, Díaz-Medina, García-Fernández (b35) 2020; 8
Garland, Heckbert (b38) 1997
Hahn, Wojtan (b6) 2016; 35
Velić, May, Moresi (b2) 2009; 8
URL . ISSN: 2380-7504.
Zhang, Garcia, Xu, Shao, Yang (b36) 2018; 100
Blender (b9) 2024
Chen, Choy, Savva, Chang, Funkhouser, Savarese (b32) 2018
Schvartzman, Otaduy (b16) 2014
Huang J, Zhan G, Fan Q, Mo K, Shao L, Chen B, Guibas L, Dong H. Generative 3D part assembly via dynamic graph learning. In: The IEEE conference on neural information processing systems. neurIPS, 2020, p. 1–12.
Zafar, Stephens, Larsson, Sakaguchi, Clive, Sampath, Museth, Blakey, Gazdik, Thomas (b12) 2010
Sellán, Luong, Mattos Da Silva, Ramakrishnan, Yang, Jacobson (b34) 2023; 42
Stutz, Geiger (b19) 2020; 128
Sellán, Chen, Wu, Garg, Jacobson (b17) 2022
Yu, Rao, Wang, Liu, Lu, Zhou (b21) 2021
Payne A, Limp F. Virtual hampson museum project.
Tsukiyama, Kondo, Kakuse, Saba, Ozaki, Itoh (b39) 1986
URL . Accepted: 2014-12-16T07:33:42Z ISSN: 1727-5288.
Koschier D, Lipponer S, Bender J. Adaptive tetrahedral meshes for brittle fracture simulation. The Eurographics Association; ISBN: 978-3-905674-61-3, 2014
Museth (b15) 2021
Zobeidi, Atanasov (b25) 2021
Manivasagam, Wang, Wong, Zeng, Sazanovich, Tan, Yang, Ma, Urtasun (b30) 2020
Oh, Shin, Jun (b11) 2012; 23
Tang J, Lei J, Xu D, Ma F, Jia K, Zhang L. SA-ConvONet: Sign-agnostic optimization of convolutional occupancy networks. In: 2021 IEEE/CVF International Conference on Computer Vision. ICCV, 2021, p. 6484–93.
Chitalu, Miao, Subr, Komura (b8) 2020; 39
Gu, Ma, Manivasagam, Zeng, Wang, Xiong, Su, Urtasun (b18) 2020
O’Brien, Bargteil, Hodgins (b4) 2002; 21
Kerbl, Kopanas, Leimkühler, Drettakis (b22) 2023; 42
Zheng, Yu, Dai, Liu (b24) 2021
Choi, Zhou, Miller, Koltun (b29) 2016
Navarro P, Cintas C, Lucena M, Fuertes JM, Rueda A, Segura R, Ogayar-Anguita C, González-José R, Delrieux C. IberianVoxel: Automatic completion of iberian ceramics for cultural heritage studies. In: Thirty-second international joint conference on artificial intelligence. Vol. 6, 2023, p. 5833–41.
Koutsoudis, Pavlidis, Arnaoutoglou, Tsiafakis, Chamzas (b33) 2009; 10
Blender (10.1016/j.cag.2024.104104_b9) 2024
Manivasagam (10.1016/j.cag.2024.104104_b30) 2020
Müller (10.1016/j.cag.2024.104104_b10) 2013; 32
Oh (10.1016/j.cag.2024.104104_b11) 2012; 23
Kerbl (10.1016/j.cag.2024.104104_b22) 2023; 42
10.1016/j.cag.2024.104104_b31
10.1016/j.cag.2024.104104_b5
Gregor (10.1016/j.cag.2024.104104_b14) 2015
Chen (10.1016/j.cag.2024.104104_b32) 2018
Ogayar-Anguita (10.1016/j.cag.2024.104104_b35) 2020; 8
Skibo (10.1016/j.cag.2024.104104_b37) 1987; 14
Deng (10.1016/j.cag.2024.104104_b20) 2023; 113
Sellán (10.1016/j.cag.2024.104104_b17) 2022
Sellán (10.1016/j.cag.2024.104104_b34) 2023; 42
Muguercia (10.1016/j.cag.2024.104104_b1) 2014; 45
Koutsoudis (10.1016/j.cag.2024.104104_b33) 2009; 10
Garland (10.1016/j.cag.2024.104104_b38) 1997
Graciano (10.1016/j.cag.2024.104104_b40) 2021; 27
Lucena (10.1016/j.cag.2024.104104_b3) 2017; 76
Schvartzman (10.1016/j.cag.2024.104104_b16) 2014
Museth (10.1016/j.cag.2024.104104_b15) 2021
Yu (10.1016/j.cag.2024.104104_b21) 2021
Zhang (10.1016/j.cag.2024.104104_b36) 2018; 100
Tsukiyama (10.1016/j.cag.2024.104104_b39) 1986
Gu (10.1016/j.cag.2024.104104_b18) 2020
10.1016/j.cag.2024.104104_b41
Zafar (10.1016/j.cag.2024.104104_b12) 2010
10.1016/j.cag.2024.104104_b23
Chitalu (10.1016/j.cag.2024.104104_b8) 2020; 39
10.1016/j.cag.2024.104104_b26
Stutz (10.1016/j.cag.2024.104104_b19) 2020; 128
10.1016/j.cag.2024.104104_b27
10.1016/j.cag.2024.104104_b28
Velić (10.1016/j.cag.2024.104104_b2) 2009; 8
Lamb (10.1016/j.cag.2024.104104_b13) 2022; 41
Zobeidi (10.1016/j.cag.2024.104104_b25) 2021
O’Brien (10.1016/j.cag.2024.104104_b4) 2002; 21
Hahn (10.1016/j.cag.2024.104104_b6) 2016; 35
Fan (10.1016/j.cag.2024.104104_b7) 2022; 41
Zheng (10.1016/j.cag.2024.104104_b24) 2021
Choi (10.1016/j.cag.2024.104104_b29) 2016
References_xml – reference: Koschier D, Lipponer S, Bender J. Adaptive tetrahedral meshes for brittle fracture simulation. The Eurographics Association; ISBN: 978-3-905674-61-3, 2014,
– volume: 128
  start-page: 1162
  year: 2020
  end-page: 1181
  ident: b19
  article-title: Learning 3D shape completion under weak supervision
  publication-title: Int J Comput Vis
– volume: 42
  year: 2023
  ident: b22
  article-title: 3D Gaussian splatting for real-time radiance field rendering
  publication-title: ACM Trans Graph (SIGGRAPH Conf Proc)
– volume: 8
  start-page: 343
  year: 2009
  end-page: 355
  ident: b2
  article-title: A fast robust algorithm for computing discrete voronoi diagrams
  publication-title: J Math Model Algorithms
– reference: , URL . ISSN: 1045-0823.
– volume: 41
  start-page: 177:1
  year: 2022
  end-page: 177:20
  ident: b7
  article-title: Simulating brittle fracture with material points
  publication-title: ACM Trans Graph
– year: 2021
  ident: b25
  article-title: A deep signed directional distance function for object shape representation
– volume: 42
  start-page: 10:1
  year: 2023
  end-page: 10:12
  ident: b34
  article-title: Breaking good: Fracture modes for realtime destruction
  publication-title: ACM Trans Graph
– volume: 41
  start-page: 65
  year: 2022
  end-page: 78
  ident: b13
  article-title: MendNet: Restoration of fractured shapes using learned occupancy functions
  publication-title: Comput Graph Forum
– reference: Navarro P, Cintas C, Lucena M, Fuertes JM, Rueda A, Segura R, Ogayar-Anguita C, González-José R, Delrieux C. IberianVoxel: Automatic completion of iberian ceramics for cultural heritage studies. In: Thirty-second international joint conference on artificial intelligence. Vol. 6, 2023, p. 5833–41.
– volume: 21
  start-page: 291
  year: 2002
  end-page: 294
  ident: b4
  article-title: Graphical modeling and animation of ductile fracture
  publication-title: ACM Trans Graph
– volume: 100
  start-page: 61
  year: 2018
  end-page: 70
  ident: b36
  article-title: Efficient voxelization using projected optimal scanline
  publication-title: Graph Models
– start-page: 15
  year: 2014
  end-page: 22
  ident: b16
  article-title: Fracture animation based on high-dimensional Voronoi diagrams
  publication-title: Proceedings of the 18th meeting of the ACM SIGGRAPH symposium on interactive 3D graphics and games
– start-page: 209
  year: 1997
  end-page: 216
  ident: b38
  article-title: Surface simplification using quadric error metrics
  publication-title: Proceedings of the 24th annual conference on computer graphics and interactive techniques
– reference: , URL . Accepted: 2014-12-16T07:33:42Z ISSN: 1727-5288.
– start-page: 7
  year: 2015
  end-page: 14
  ident: b14
  article-title: Automatic 3D object fracturing for evaluation of partial retrieval and object restoration tasks - benchmark and application to 3D cultural heritage data
  publication-title: 3DOR
– year: 2018
  ident: b32
  article-title: Text2Shape: Generating shapes from natural language by learning joint embeddings
– start-page: 1
  year: 2021
  end-page: 197
  ident: b15
  article-title: OPENVDB
  publication-title: ACM SIGGRAPH 2021 courses
– volume: 23
  year: 2012
  ident: b11
  article-title: Practical simulation of hierarchical brittle fracture
  publication-title: Comput. Animat. Virtual Worlds
– reference: Tang J, Lei J, Xu D, Ma F, Jia K, Zhang L. SA-ConvONet: Sign-agnostic optimization of convolutional occupancy networks. In: 2021 IEEE/CVF International Conference on Computer Vision. ICCV, 2021, p. 6484–93.
– start-page: 12498
  year: 2021
  end-page: 12507
  ident: b21
  article-title: PoinTr: Diverse point cloud completion with geometry-aware transformers
  publication-title: ICCV
– reference: Huang J, Zhan G, Fan Q, Mo K, Shao L, Chen B, Guibas L, Dong H. Generative 3D part assembly via dynamic graph learning. In: The IEEE conference on neural information processing systems. neurIPS, 2020, p. 1–12.
– volume: 39
  start-page: 569
  year: 2020
  end-page: 583
  ident: b8
  article-title: Displacement-Correlated XFEM for simulating brittle fracture
  publication-title: Comput Graph Forum
– reference: Cheng Y-C, Lee H-Y, Tulyakov S, Schwing AG, Gui L-Y. SDFusion: Multimodal 3D shape completion, reconstruction, and generation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023, p. 4456–65, URL.
– start-page: 1
  year: 2010
  ident: b12
  article-title: Destroying LA for ”2012”
  publication-title: ACM SIGGRAPH 2010 talks
– reference: , URL . ISSN: 2380-7504.
– volume: 32
  start-page: 115:1
  year: 2013
  end-page: 115:10
  ident: b10
  article-title: Real time dynamic fracture with volumetric approximate convex decompositions
  publication-title: ACM Trans Graph
– year: 1986
  ident: b39
  article-title: Method and system for data compression and restoration
– year: 2016
  ident: b29
  article-title: A large dataset of object scans
– volume: 8
  start-page: 12675
  year: 2020
  end-page: 12687
  ident: b35
  article-title: A GPU-based framework for generating implicit datasets of voxelized polygonal models for the training of 3D convolutional neural networks
  publication-title: IEEE Access
– year: 2021
  ident: b24
  article-title: Deep implicit templates for 3D shape representation
– reference: Payne A, Limp F. Virtual hampson museum project.
– volume: 113
  start-page: 102
  year: 2023
  end-page: 112
  ident: b20
  article-title: TAssembly: Data-driven fractured object assembly using a linear template model
  publication-title: Comput Graph
– volume: 10
  start-page: 281
  year: 2009
  end-page: 295
  ident: b33
  article-title: Qp: A tool for generating 3D models of ancient Greek pottery
  publication-title: J. Cult. Herit.
– start-page: 283
  year: 2020
  end-page: 299
  ident: b18
  article-title: Weakly-supervised 3D shape completion in the wild
  publication-title: Computer vision – ECCV 2020
– reference: Behley J, Garbade M, Milioto A, Quenzel J, Behnke S, Stachniss C, Gall J. SemanticKITTI: A dataset for semantic scene understanding of lidar sequences. In: 2019 IEEE/CVF international conference on computer vision (ICCV). 2019, p. 9296–306.
– year: 2022
  ident: b17
  article-title: Breaking Bad: A dataset for geometric fracture and reassembly
– reference: , URL . Conference Name: 2021 IEEE/CVF International Conference on Computer Vision (ICCV) ISBN: 9781665428125 Place: Montreal, QC, Canada Publisher: IEEE.
– start-page: 11164
  year: 2020
  end-page: 11173
  ident: b30
  article-title: LiDARsim: Realistic LiDAR simulation by leveraging the real world
  publication-title: 2020 IEEE/CVF conference on computer vision and pattern recognition
– volume: 45
  start-page: 86
  year: 2014
  end-page: 100
  ident: b1
  article-title: Fracture modeling in computer graphics
  publication-title: Comput Graph
– volume: 14
  start-page: 83
  year: 1987
  end-page: 96
  ident: b37
  article-title: The effects of water on processes of ceramic abrasion
  publication-title: J Archaeol Sci
– year: 2024
  ident: b9
  article-title: Cell fracture: Blender 4.1 manual
– volume: 27
  start-page: 3733
  year: 2021
  end-page: 3744
  ident: b40
  article-title: QuadStack: An efficient representation and direct rendering of layered datasets
  publication-title: IEEE Trans Vis Comput Graphics
– volume: 76
  start-page: 21565
  year: 2017
  end-page: 21577
  ident: b3
  article-title: Classification of archaeological pottery profiles using modal analysis
  publication-title: Multimedia Tools Appl
– volume: 35
  start-page: 104:1
  year: 2016
  end-page: 104:11
  ident: b6
  article-title: Fast approximations for boundary element based brittle fracture simulation
  publication-title: ACM Trans Graph
– volume: 14
  start-page: 83
  issue: 1
  year: 1987
  ident: 10.1016/j.cag.2024.104104_b37
  article-title: The effects of water on processes of ceramic abrasion
  publication-title: J Archaeol Sci
  doi: 10.1016/S0305-4403(87)80008-0
– year: 1986
  ident: 10.1016/j.cag.2024.104104_b39
– ident: 10.1016/j.cag.2024.104104_b5
– volume: 42
  issue: 4
  year: 2023
  ident: 10.1016/j.cag.2024.104104_b22
  article-title: 3D Gaussian splatting for real-time radiance field rendering
  publication-title: ACM Trans Graph (SIGGRAPH Conf Proc)
– start-page: 15
  year: 2014
  ident: 10.1016/j.cag.2024.104104_b16
  article-title: Fracture animation based on high-dimensional Voronoi diagrams
– volume: 10
  start-page: 281
  issue: 2
  year: 2009
  ident: 10.1016/j.cag.2024.104104_b33
  article-title: Qp: A tool for generating 3D models of ancient Greek pottery
  publication-title: J. Cult. Herit.
  doi: 10.1016/j.culher.2008.07.012
– ident: 10.1016/j.cag.2024.104104_b23
  doi: 10.24963/ijcai.2023/647
– year: 2024
  ident: 10.1016/j.cag.2024.104104_b9
– year: 2021
  ident: 10.1016/j.cag.2024.104104_b24
– volume: 32
  start-page: 115:1
  issue: 4
  year: 2013
  ident: 10.1016/j.cag.2024.104104_b10
  article-title: Real time dynamic fracture with volumetric approximate convex decompositions
  publication-title: ACM Trans Graph
  doi: 10.1145/2461912.2461934
– volume: 128
  start-page: 1162
  issue: 5
  year: 2020
  ident: 10.1016/j.cag.2024.104104_b19
  article-title: Learning 3D shape completion under weak supervision
  publication-title: Int J Comput Vis
  doi: 10.1007/s11263-018-1126-y
– volume: 35
  start-page: 104:1
  issue: 4
  year: 2016
  ident: 10.1016/j.cag.2024.104104_b6
  article-title: Fast approximations for boundary element based brittle fracture simulation
  publication-title: ACM Trans Graph
  doi: 10.1145/2897824.2925902
– year: 2016
  ident: 10.1016/j.cag.2024.104104_b29
– volume: 39
  start-page: 569
  issue: 2
  year: 2020
  ident: 10.1016/j.cag.2024.104104_b8
  article-title: Displacement-Correlated XFEM for simulating brittle fracture
  publication-title: Comput Graph Forum
  doi: 10.1111/cgf.13953
– volume: 45
  start-page: 86
  year: 2014
  ident: 10.1016/j.cag.2024.104104_b1
  article-title: Fracture modeling in computer graphics
  publication-title: Comput Graph
  doi: 10.1016/j.cag.2014.08.006
– start-page: 12498
  year: 2021
  ident: 10.1016/j.cag.2024.104104_b21
  article-title: PoinTr: Diverse point cloud completion with geometry-aware transformers
– start-page: 1
  year: 2010
  ident: 10.1016/j.cag.2024.104104_b12
  article-title: Destroying LA for ”2012”
– volume: 41
  start-page: 177:1
  issue: 5
  year: 2022
  ident: 10.1016/j.cag.2024.104104_b7
  article-title: Simulating brittle fracture with material points
  publication-title: ACM Trans Graph
  doi: 10.1145/3522573
– start-page: 7
  year: 2015
  ident: 10.1016/j.cag.2024.104104_b14
  article-title: Automatic 3D object fracturing for evaluation of partial retrieval and object restoration tasks - benchmark and application to 3D cultural heritage data
– volume: 113
  start-page: 102
  year: 2023
  ident: 10.1016/j.cag.2024.104104_b20
  article-title: TAssembly: Data-driven fractured object assembly using a linear template model
  publication-title: Comput Graph
  doi: 10.1016/j.cag.2023.05.003
– volume: 21
  start-page: 291
  issue: 3
  year: 2002
  ident: 10.1016/j.cag.2024.104104_b4
  article-title: Graphical modeling and animation of ductile fracture
  publication-title: ACM Trans Graph
  doi: 10.1145/566654.566579
– volume: 27
  start-page: 3733
  issue: 9
  year: 2021
  ident: 10.1016/j.cag.2024.104104_b40
  article-title: QuadStack: An efficient representation and direct rendering of layered datasets
  publication-title: IEEE Trans Vis Comput Graphics
  doi: 10.1109/TVCG.2020.2981565
– ident: 10.1016/j.cag.2024.104104_b31
  doi: 10.1109/ICCV.2019.00939
– ident: 10.1016/j.cag.2024.104104_b28
– ident: 10.1016/j.cag.2024.104104_b41
– start-page: 1
  year: 2021
  ident: 10.1016/j.cag.2024.104104_b15
  article-title: OPENVDB
– volume: 41
  start-page: 65
  issue: 5
  year: 2022
  ident: 10.1016/j.cag.2024.104104_b13
  article-title: MendNet: Restoration of fractured shapes using learned occupancy functions
  publication-title: Comput Graph Forum
  doi: 10.1111/cgf.14603
– year: 2018
  ident: 10.1016/j.cag.2024.104104_b32
– year: 2021
  ident: 10.1016/j.cag.2024.104104_b25
– volume: 8
  start-page: 12675
  year: 2020
  ident: 10.1016/j.cag.2024.104104_b35
  article-title: A GPU-based framework for generating implicit datasets of voxelized polygonal models for the training of 3D convolutional neural networks
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.2965624
– start-page: 209
  year: 1997
  ident: 10.1016/j.cag.2024.104104_b38
  article-title: Surface simplification using quadric error metrics
– year: 2022
  ident: 10.1016/j.cag.2024.104104_b17
– volume: 8
  start-page: 343
  issue: 3
  year: 2009
  ident: 10.1016/j.cag.2024.104104_b2
  article-title: A fast robust algorithm for computing discrete voronoi diagrams
  publication-title: J Math Model Algorithms
  doi: 10.1007/s10852-008-9097-6
– ident: 10.1016/j.cag.2024.104104_b27
  doi: 10.1109/CVPR52729.2023.00433
– start-page: 283
  year: 2020
  ident: 10.1016/j.cag.2024.104104_b18
  article-title: Weakly-supervised 3D shape completion in the wild
– volume: 76
  start-page: 21565
  issue: 20
  year: 2017
  ident: 10.1016/j.cag.2024.104104_b3
  article-title: Classification of archaeological pottery profiles using modal analysis
  publication-title: Multimedia Tools Appl
  doi: 10.1007/s11042-016-4076-9
– ident: 10.1016/j.cag.2024.104104_b26
  doi: 10.1109/ICCV48922.2021.00644
– volume: 23
  year: 2012
  ident: 10.1016/j.cag.2024.104104_b11
  article-title: Practical simulation of hierarchical brittle fracture
  publication-title: Comput. Animat. Virtual Worlds
  doi: 10.1002/cav.1443
– volume: 100
  start-page: 61
  year: 2018
  ident: 10.1016/j.cag.2024.104104_b36
  article-title: Efficient voxelization using projected optimal scanline
  publication-title: Graph Models
  doi: 10.1016/j.gmod.2017.06.004
– start-page: 11164
  year: 2020
  ident: 10.1016/j.cag.2024.104104_b30
  article-title: LiDARsim: Realistic LiDAR simulation by leveraging the real world
– volume: 42
  start-page: 10:1
  issue: 1
  year: 2023
  ident: 10.1016/j.cag.2024.104104_b34
  article-title: Breaking good: Fracture modes for realtime destruction
  publication-title: ACM Trans Graph
  doi: 10.1145/3549540
SSID ssj0002264
Score 2.3902955
Snippet One of the primary challenges inherent in utilizing deep learning models is the scarcity and accessibility hurdles associated with acquiring datasets of...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 104104
SubjectTerms Fracture dataset
Fragmentation
GPU programming
Voronoi
Voxel
Title Generating implicit object fragment datasets for machine learning
URI https://dx.doi.org/10.1016/j.cag.2024.104104
Volume 125
WOSCitedRecordID wos001403099000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 0097-8493
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0002264
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lj9MwELagywEOiKfY5aEcOFFllSZxHR8LWgSr1YLEgnqLbGcSdVWSKknR7r9n_Eqj8hAgcbGiOE7a-WxnMvPNDCEvpcz4DKIi1LprmEopwkxREUoBVEAms8KU8_lyxs7Ps-WSf3Q1WztTToDVdXZ1xTf_FWo8h2Dr0Nm_gHu4KZ7AYwQdW4Qd2z8C3iaSNmzmlaGLr_ppI7W5ZVq2ojLOf80L7aA3uRimXw2fEnwBiWqsr_qiD52ZIia79Ygef6bd7K-TjbVCL9Yl_qdmcOFsoRAuPwFuHM309Hgw50C1ba3WKkoB61HXh0pcCxeb2K6bznc5w0Sc7pE8hoiZHT3J7MAc34qprYo47MA29vmH3dwaFi7xS7061k_QDmlXrXgvSfYnE4-Ct9WU2Djh9CY5iBnl2YQcLN6fLE-Ht7MOHLaZSe3v8J5uw_nbe9DPdZWR_nFxj9x1Hw7BwgJ-n9yA-gG5M0on-ZAsdtAHHvrAQh946AMPfYDQBw76wEP_iHx-e3Lx5l3oSmSEKuasD4GnFHiSliCoKlicFLgoWax4AkLi_szKRGHXDCQVNC4iwYoMG8ESVYpI8uQxmdRNDU9IoJI5m8E8AlyhKS0ZF0JKXuAaz-YUIjgkkRdGrlz-eF3GZJ17ouBljvLLtfxyK79D8moYsrHJU353ceolnDvtz2p1OU6HXw87-rdhT8nt3Zx9RiZ9u4Xn5Jb61q-69oWbNN8BKHx-DA
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Generating+implicit+object+fragment+datasets+for+machine+learning&rft.jtitle=Computers+%26+graphics&rft.au=L%C3%B3pez%2C+Alfonso&rft.au=Rueda%2C+Antonio+J.&rft.au=Segura%2C+Rafael+J.&rft.au=Ogayar%2C+Carlos+J.&rft.date=2024-12-01&rft.pub=Elsevier+Ltd&rft.issn=0097-8493&rft.volume=125&rft_id=info:doi/10.1016%2Fj.cag.2024.104104&rft.externalDocID=S0097849324002395
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0097-8493&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0097-8493&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0097-8493&client=summon