Ir al contenido (pulsa Retorno)

Universitat Politècnica de Catalunya

    • Català
    • Castellano
    • English
    • LoginRegisterLog in (no UPC users)
  • mailContact Us
  • world English 
    • Català
    • Castellano
    • English
  • userLogin   
      LoginRegisterLog in (no UPC users)

UPCommons. Global access to UPC knowledge

Banner header
69.147 UPC E-Prints
You are here:
View Item 
  •   DSpace Home
  • E-prints
  • Departaments
  • Departament de Ciències de la Computació
  • Articles de revista
  • View Item
  •   DSpace Home
  • E-prints
  • Departaments
  • Departament de Ciències de la Computació
  • Articles de revista
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Enabling viewpoint learning through dynamic label generation

Thumbnail
View/Open
cgf.142643.pdf (20,33Mb)
 
10.1111/cgf.142643
 
  View UPCommons Usage Statistics
  LA Referencia / Recolecta stats
Includes usage data since 2022
Cita com:
hdl:2117/353328

Show full item record
Schelling, Michael
Hermosilla Casajús, Pedro
Vázquez Alcocer, Pere PauMés informacióMés informacióMés informació
Ropinski, Timo
Document typeArticle
Defense date2021-05
Rights accessOpen Access
Attribution-NonCommercial 4.0 International
This work is protected by the corresponding intellectual and industrial property rights. Except where otherwise noted, its contents are licensed under a Creative Commons license : Attribution-NonCommercial 4.0 International
ProjectVISUALIZACION, MODELADO, SIMULACION E INTERACCION CON MODELOS 3D. APLICACIONES EN CIENCIAS DE LA VIDA Y ENTORNOS RURALES Y URBANOS (AEI-TIN2017-88515-C2-1-R)
Abstract
Optimal viewpoint prediction is an essential task in many computer graphics applications. Unfortunately, common viewpointqualities suffer from two major drawbacks: dependency on clean surface meshes, which are not always available, and the lack ofclosed-form expressions, which requires a costly search involving rendering. To overcome these limitations we propose to sepa-rate viewpoint selection from rendering through an end-to-end learning approach, whereby we reduce the in¿uence of the meshquality by predicting viewpoints from unstructured point clouds instead of polygonal meshes. While this makes our approachinsensitive to the mesh discretization during evaluation, it only becomes possible when resolving label ambiguities that arise inthis context. Therefore, we additionally propose to incorporate the label generation into the training procedure, making the labeldecision adaptive to the current network predictions. We show how our proposed approach allows for learning viewpoint pre-dictions for models from different object categories and for different viewpoint qualities. Additionally, we show that predictiontimes are reduced from several minutes to a fraction of a second, as compared to state-of-the-art (SOTA) viewpoint quality eval-uation. Code and training data is available at https://github.com/schellmi42/viewpoint_learning, whichis to our knowledge the biggest viewpoint quality dataset available.
CitationSchelling, M.; Hermosilla, P.; Vázquez, P., Ropinski, T. Enabling viewpoint learning through dynamic label generation. "Computer graphics forum", Maig 2021, vol. 40, núm. 2, p. 413-423. 
URIhttp://hdl.handle.net/2117/353328
DOI10.1111/cgf.142643
ISSN1467-8659
Publisher versionhttps://onlinelibrary.wiley.com/doi/10.1111/cgf.142643
Collections
  • Departament de Ciències de la Computació - Articles de revista [1.125]
  • ViRVIG - Grup de Recerca en Visualització, Realitat Virtual i Interacció Gràfica - Articles de revista [113]
  View UPCommons Usage Statistics

Show full item record

FilesDescriptionSizeFormatView
cgf.142643.pdf20,33MbPDFView/Open

Browse

This CollectionBy Issue DateAuthorsOther contributionsTitlesSubjectsThis repositoryCommunities & CollectionsBy Issue DateAuthorsOther contributionsTitlesSubjects

© UPC Obrir en finestra nova . Servei de Biblioteques, Publicacions i Arxius

info.biblioteques@upc.edu

  • About This Repository
  • Metadata under:Metadata under CC0
  • Contact Us
  • Send Feedback
  • Privacy Settings
  • Inici de la pàgina