Latent-space laplacian pyramids for adversarial representation learning with 3D point clouds

Vage Egiazarian, Savva Ignatyev, Alexey Artemov, Oleg Voynov, Andrey Kravchenko, Youyi Zheng, Luiz Velho, Evgeny Burnaev

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Abstract

    Constructing high-quality generative models for 3D shapes is a fundamental task in computer vision with diverse applications in geometry processing, engineering, and design. Despite the recent progress in deep generative modelling, synthesis of finely detailed 3D surfaces, such as high-resolution point clouds, from scratch has not been achieved with existing learning-based approaches. In this work, we propose to employ the latent-space Laplacian pyramid representation within a hierarchical generative model for 3D point clouds. We combine the latent-space GAN and Laplacian GAN architectures proposed in the recent years to form a multi-scale model capable of generating 3D point clouds at increasing levels of detail. Our initial evaluation demonstrates that our model outperforms the existing generative models for 3D point clouds, emphasizing the need for an in-depth comparative study on the topic of multi-stage generative learning with point clouds.

    Original languageEnglish
    Title of host publicationVISAPP
    EditorsGiovanni Maria Farinella, Petia Radeva, Jose Braz
    PublisherSciTePress
    Pages421-428
    Number of pages8
    ISBN (Electronic)9789897584022
    Publication statusPublished - 2020
    Event15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2020 - Valletta, Malta
    Duration: 27 Feb 202029 Feb 2020

    Publication series

    NameVISIGRAPP 2020 - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
    Volume4

    Conference

    Conference15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2020
    Country/TerritoryMalta
    CityValletta
    Period27/02/2029/02/20

    Keywords

    • 3D Point Clouds
    • Deep Learning
    • Generative Adversarial Networks
    • Multi-scale 3D Modelling

    Fingerprint

    Dive into the research topics of 'Latent-space laplacian pyramids for adversarial representation learning with 3D point clouds'. Together they form a unique fingerprint.

    Cite this