Sketch-Aided Retrieval of Incomplete 3D Cultural Heritage Objects

Stefan Lengauer, Alexander Komar, Arniel Labrada, Stephan Karl, Elisabeth Trinkl, Reinhold Preiner, Benjamin Bustos, Tobias Schreck

Publikation: KonferenzbeitragPaperForschungBegutachtung

Abstract

Due to advances in digitization technology, documentation efforts and digital library systems, increasingly large collections of visual Cultural Heritage (CH) object data becomes available, offering rich opportunities for domain analysis, e.g., for comparing, tracing and studying objects created over time. In principle, existing shape- and image-based similarity search methods can aid such domain analysis tasks. However, in practice, visual object data are given in different modalities, including 2D, 3D, sketches or conventional drawings like profile sections or unwrappings. In addition, collections may be distributed across different publications and repositories, posing a challenge for implementing encompassing search and analysis systems. We introduce a methodology and system for cross-modal visual search in CH object data. Specifically, we propose a new query modality based on 3D views enhanced by user sketches (3D+sketch). This allows for adding new context to the search, which is useful e.g., for searching based on incomplete query objects, or for testing hypotheses on existence of certain shapes in a collection. We present an appropriately designed workflow for constructing query views from incomplete 3D objects enhanced by a user sketch based on shape completion and texture inpainting. Visual cues additionally help users compare retrieved objects with the query. We apply our method on a set of relevant 3D and view-based CH object data, demonstrating the feasibility of our approach and its potential to support analysis of domain experts in Archaeology and the field of CH in general.
Originalspracheenglisch
Seitenumfang8
DOIs
PublikationsstatusVeröffentlicht - 2019
Veranstaltung12th Eurographics Workshop on 3D Object Retrieval - Genova, Italien
Dauer: 5 Mai 20196 Mai 2019
http://3dor2019.ge.imati.cnr.it/

Workshop

Workshop12th Eurographics Workshop on 3D Object Retrieval
LandItalien
OrtGenova
Zeitraum5/05/196/05/19
Internetadresse

Fingerprint

Digital libraries
Analog to digital conversion
Textures
Testing

Dies zitieren

Lengauer, S., Komar, A., Labrada, A., Karl, S., Trinkl, E., Preiner, R., ... Schreck, T. (2019). Sketch-Aided Retrieval of Incomplete 3D Cultural Heritage Objects. Beitrag in 12th Eurographics Workshop on 3D Object Retrieval, Genova, Italien. https://doi.org/10.2312/3dor.20191057

Sketch-Aided Retrieval of Incomplete 3D Cultural Heritage Objects. / Lengauer, Stefan; Komar, Alexander; Labrada, Arniel; Karl, Stephan; Trinkl, Elisabeth; Preiner, Reinhold; Bustos, Benjamin; Schreck, Tobias.

2019. Beitrag in 12th Eurographics Workshop on 3D Object Retrieval, Genova, Italien.

Publikation: KonferenzbeitragPaperForschungBegutachtung

Lengauer, S, Komar, A, Labrada, A, Karl, S, Trinkl, E, Preiner, R, Bustos, B & Schreck, T 2019, 'Sketch-Aided Retrieval of Incomplete 3D Cultural Heritage Objects' Beitrag in, Genova, Italien, 5/05/19 - 6/05/19, . https://doi.org/10.2312/3dor.20191057
Lengauer S, Komar A, Labrada A, Karl S, Trinkl E, Preiner R et al. Sketch-Aided Retrieval of Incomplete 3D Cultural Heritage Objects. 2019. Beitrag in 12th Eurographics Workshop on 3D Object Retrieval, Genova, Italien. https://doi.org/10.2312/3dor.20191057
Lengauer, Stefan ; Komar, Alexander ; Labrada, Arniel ; Karl, Stephan ; Trinkl, Elisabeth ; Preiner, Reinhold ; Bustos, Benjamin ; Schreck, Tobias. / Sketch-Aided Retrieval of Incomplete 3D Cultural Heritage Objects. Beitrag in 12th Eurographics Workshop on 3D Object Retrieval, Genova, Italien.8 S.
@conference{fde638bbc4d2477fa2882068f4b46717,
title = "Sketch-Aided Retrieval of Incomplete 3D Cultural Heritage Objects",
abstract = "Due to advances in digitization technology, documentation efforts and digital library systems, increasingly large collections of visual Cultural Heritage (CH) object data becomes available, offering rich opportunities for domain analysis, e.g., for comparing, tracing and studying objects created over time. In principle, existing shape- and image-based similarity search methods can aid such domain analysis tasks. However, in practice, visual object data are given in different modalities, including 2D, 3D, sketches or conventional drawings like profile sections or unwrappings. In addition, collections may be distributed across different publications and repositories, posing a challenge for implementing encompassing search and analysis systems. We introduce a methodology and system for cross-modal visual search in CH object data. Specifically, we propose a new query modality based on 3D views enhanced by user sketches (3D+sketch). This allows for adding new context to the search, which is useful e.g., for searching based on incomplete query objects, or for testing hypotheses on existence of certain shapes in a collection. We present an appropriately designed workflow for constructing query views from incomplete 3D objects enhanced by a user sketch based on shape completion and texture inpainting. Visual cues additionally help users compare retrieved objects with the query. We apply our method on a set of relevant 3D and view-based CH object data, demonstrating the feasibility of our approach and its potential to support analysis of domain experts in Archaeology and the field of CH in general.",
author = "Stefan Lengauer and Alexander Komar and Arniel Labrada and Stephan Karl and Elisabeth Trinkl and Reinhold Preiner and Benjamin Bustos and Tobias Schreck",
year = "2019",
doi = "10.2312/3dor.20191057",
language = "English",
note = "12th Eurographics Workshop on 3D Object Retrieval ; Conference date: 05-05-2019 Through 06-05-2019",
url = "http://3dor2019.ge.imati.cnr.it/",

}

TY - CONF

T1 - Sketch-Aided Retrieval of Incomplete 3D Cultural Heritage Objects

AU - Lengauer, Stefan

AU - Komar, Alexander

AU - Labrada, Arniel

AU - Karl, Stephan

AU - Trinkl, Elisabeth

AU - Preiner, Reinhold

AU - Bustos, Benjamin

AU - Schreck, Tobias

PY - 2019

Y1 - 2019

N2 - Due to advances in digitization technology, documentation efforts and digital library systems, increasingly large collections of visual Cultural Heritage (CH) object data becomes available, offering rich opportunities for domain analysis, e.g., for comparing, tracing and studying objects created over time. In principle, existing shape- and image-based similarity search methods can aid such domain analysis tasks. However, in practice, visual object data are given in different modalities, including 2D, 3D, sketches or conventional drawings like profile sections or unwrappings. In addition, collections may be distributed across different publications and repositories, posing a challenge for implementing encompassing search and analysis systems. We introduce a methodology and system for cross-modal visual search in CH object data. Specifically, we propose a new query modality based on 3D views enhanced by user sketches (3D+sketch). This allows for adding new context to the search, which is useful e.g., for searching based on incomplete query objects, or for testing hypotheses on existence of certain shapes in a collection. We present an appropriately designed workflow for constructing query views from incomplete 3D objects enhanced by a user sketch based on shape completion and texture inpainting. Visual cues additionally help users compare retrieved objects with the query. We apply our method on a set of relevant 3D and view-based CH object data, demonstrating the feasibility of our approach and its potential to support analysis of domain experts in Archaeology and the field of CH in general.

AB - Due to advances in digitization technology, documentation efforts and digital library systems, increasingly large collections of visual Cultural Heritage (CH) object data becomes available, offering rich opportunities for domain analysis, e.g., for comparing, tracing and studying objects created over time. In principle, existing shape- and image-based similarity search methods can aid such domain analysis tasks. However, in practice, visual object data are given in different modalities, including 2D, 3D, sketches or conventional drawings like profile sections or unwrappings. In addition, collections may be distributed across different publications and repositories, posing a challenge for implementing encompassing search and analysis systems. We introduce a methodology and system for cross-modal visual search in CH object data. Specifically, we propose a new query modality based on 3D views enhanced by user sketches (3D+sketch). This allows for adding new context to the search, which is useful e.g., for searching based on incomplete query objects, or for testing hypotheses on existence of certain shapes in a collection. We present an appropriately designed workflow for constructing query views from incomplete 3D objects enhanced by a user sketch based on shape completion and texture inpainting. Visual cues additionally help users compare retrieved objects with the query. We apply our method on a set of relevant 3D and view-based CH object data, demonstrating the feasibility of our approach and its potential to support analysis of domain experts in Archaeology and the field of CH in general.

U2 - 10.2312/3dor.20191057

DO - 10.2312/3dor.20191057

M3 - Paper

ER -