Centre de documentation
scientifique

Deep learning-based point cloud compression / Maurice Quach (2022)  

Public Titre : Deep learning-based point cloud compression Titre original : Compression de nuages de points par apprentissage profond Type de document : Thèse/HDR Auteurs : Maurice Quach, Auteur ; Frédéric Dufaux, Directeur de thèse ; Giuseppe Valenzise, Directeur de thèse Editeur : Bures-sur-Yvette : Université Paris-Saclay Année de publication : 2022 Importance : 165 p. Format : 21 x 30 cm Note générale : Bibliographie Thèse de Doctorat de l'Université de Saclay, spécialité Traitement du signal et des images Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] apprentissage profond [Termes IGN] attribut [Termes IGN] compression d'image [Termes IGN] compression de données [Termes IGN] géométrie [Termes IGN] semis de points [Termes IGN] stockage de données Index. décimale : THESE Thèses et HDR Résumé : (auteur) Point clouds are becoming essential in key applications with advances in capture technologies leading to large volumes of data.Compression is thus essential for storage and transmission.Point Cloud Compression can be divided into two parts: geometry and attribute compression.In addition, point cloud quality assessment is necessary in order to evaluate point cloud compression methods.Geometry compression, attribute compression and quality assessment form the three main parts of this dissertation.The common challenge across these three problems is the sparsity and irregularity of point clouds.Indeed, while other modalities such as images lie on a regular grid, point cloud geometry can be considered as a sparse binary signal over 3D space and attributes are defined on the geometry which can be both sparse and irregular.First, the state of the art for geometry and attribute compression methods with a focus on deep learning based approaches is reviewed.The challenges faced when compressing geometry and attributes are considered, with an analysis of the current approaches to address them, their limitations and the relations between deep learning and traditional ones.We present our work on geometry compression: a convolutional lossy geometry compression approach with a study on the key performance factors of such methods and a generative model for lossless geometry compression with a multiscale variant addressing its complexity issues.Then, we present a folding-based approach for attribute compression that learns a mapping from the point cloud to a 2D grid in order to reduce point cloud attribute compression to an image compression problem.Furthermore, we propose a differentiable deep perceptual quality metric that can be used to train lossy point cloud geometry compression networks while being well correlated with perceived visual quality and a convolutional neural network for point cloud quality assessment based on a patch extraction approach.Finally, we conclude the dissertation and discuss open questions in point cloud compression, existing solutions and perspectives. We highlight the link between existing point cloud compression research and research problems to relevant areas of adjacent fields, such as rendering in computer graphics, mesh compression and point cloud quality assessment. Note de contenu : 1- Introduction 2- State of the Art on point cloud compression 3- Convolutional neural networks for lossy PCGC 4- Deep generative model for lossless PCGC 5- Deep multiscale lossless PCGC 6- Folding-based PCAC 7- Deep perceptual point cloud quality metric 8- Convolutional Neural Network for PCQA Numéro de notice : 24081 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de doctorat : Traitement du signal et des images : Paris-Saclay : 2022 Organisme de stage : Laboratoire des signaux et systèmes DOI : sans En ligne : https://theses.hal.science/tel-03894261 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102331