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
69.161 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.

Monte Carlo convolution for learning on non-uniformly sampled point clouds

Thumbnail
View/Open
Versió publicada pel l'editor. En accés obert a l'ACM Digital library. (16,10Mb)
 
10.1145/3272127.3275110
 
  View UPCommons Usage Statistics
  LA Referencia / Recolecta stats
Includes usage data since 2022
Cita com:
hdl:2117/128030

Show full item record
Hermosilla Casajús, Pedro
Ristchel, Tobias
Vázquez Alcocer, Pere PauMés informacióMés informacióMés informació
Vinacua Pla, ÁlvaroMés informacióMés informacióMés informació
Ropinski, Timo
Document typeArticle
Defense date2018-11
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder
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
Deep learning systems extensively use convolution operations to process input data. Though convolution is clearly defined for structured data such as 2D images or 3D volumes, this is not true for other data types such as sparse point clouds. Previous techniques have developed approximations to convolutions for restricted conditions. Unfortunately, their applicability is limited and cannot be used for general point clouds. We propose an efficient and effective method to learn convolutions for non-uniformly sampled point clouds, as they are obtained with modern acquisition techniques. Learning is enabled by four key novelties: first, representing the convolution kernel itself as a multilayer perceptron; second, phrasing convolution as a Monte Carlo integration problem, third, using this notion to combine information from multiple samplings at different levels; and fourth using Poisson disk sampling as a scalable means of hierarchical point cloud learning. The key idea across all these contributions is to guarantee adequate consideration of the underlying non-uniform sample distribution function from a Monte Carlo perspective. To make the proposed concepts applicable to real-world tasks, we furthermore propose an efficient implementation which significantly reduces the GPU memory required during the training process. By employing our method in hierarchical network architectures we can outperform most of the state-of-the-art networks on established point cloud segmentation, classification and normal estimation benchmarks. Furthermore, in contrast to most existing approaches, we also demonstrate the robustness of our method with respect to sampling variations, even when training with uniformly sampled data only. To support the direct application of these concepts, we provide a ready-to-use TensorFlow implementation of these layers at https://github.com/viscom-ulm/MCCNN.
CitationHermosilla, P. [et al.]. Monte Carlo convolution for learning on non-uniformly sampled point clouds. "ACM transactions on graphics", Novembre 2018, vol. 37, núm. 6, p. 235:1-235:12. 
URIhttp://hdl.handle.net/2117/128030
DOI10.1145/3272127.3275110
ISSN0730-0301
Publisher versionhttps://dl.acm.org/citation.cfm?id=3275110
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
a235-hermosilla.pdfVersió publicada pel l'editor. En accés obert a l'ACM Digital library.16,10MbPDFView/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