Vous êtes ici : Accueil » Réunions » Réunion

Identification

Identifiant: 
Mot de passe : 

Mot de passe oublié ?
Détails d'identification oubliés ?

Évaluation de la qualité subjective et objective des données 3D

Nous vous rappelons que, afin de garantir l'accès de tous les inscrits aux salles de réunion, l'inscription aux réunions est gratuite mais obligatoire.

Inscriptions closes à cette réunion.

Inscriptions

59 personnes membres du GdR ISIS, et 30 personnes non membres du GdR, sont inscrits à cette réunion.
Capacité de la salle : 90 personnes.

Réunion d'animation en visio-conférence

La réunion aura lieu en visioconférence. Cependant pour des raisons techniques liées au nombre de connexions simultanées, l'inscription aux réunions est gratuite, mais obligatoire.

Les identifiants de connexion sont communiquées par mail aux inscrits la veille ou le matin de la réunion.

Annonce

De nos jours, la visualisation de données se démocratise à travers l'accès des nouvelles technologies au grand public. Parmi ces données, l'estimation de la qualité des données 3D est un champ de recherche en plein essor de par l'utilisation accrue de la 3D notamment pour la réalité virtuelle pour différentes applications : médicales, enseignements, formations, conférences, etc. La situation actuelle (Covid-19) laisse envisager un déploiement considérable de ces nouvelles technologies.

La masse de données à traiter étant conséquente et sujette à des diverses distorsions dues à la compression, la transmission ou bien encore le support utilisé pour l’affichage, il convient de disposer d'outils pertinents permettant d'évaluer l'impact perceptuel de ces distorsions afin garantir une qualité d'expérience satisfaisante.

Cette demi-journée du thème B a pour objectif de donner un aperçu des travaux de recherche liés à l'estimation de la qualité des données 3D (subjective, objective, compression, dégradation, etc.).

Date :

Mardi 2 juin, à 14h.

Organisateur :

Aladine Chetouani, Laboratoire PRISME, Université d'Orléans, Orléans, aladine.chetouani@univ-orleans.fr

Programme

Résumés des contributions

QoE and Immersive Media

Patrick Le Callet, LS2N, Nantes

Learning Convolutional Transforms For Lossy Point Cloud Geometry Compression

Maurice Quach, Giuseppe Valenzise, Frederic Dufaux, L2S, CNRS, CentraleSupelec

Efficient point cloud compression is fundamental to enable the deployment of virtual and mixed reality applications, since the number of points to code can range in the order of millions. In this paper, we present a novel data-driven geometry compression method for static point clouds based on learned convolutional transforms and uniform quantization. We perform joint optimization of both rate and distortion using a trade-off parameter. In addition, we cast the decoding process as a binary classification of the point cloud occupancy map. Our method outperforms the MPEG reference solution in terms of rate-distortion on the Microsoft Voxelized Upper Bodies dataset with 51.5% BDBR savings on average. Moreover, while octree-based methods face exponential diminution of the number of points at low bitrates, our method still produces high resolution outputs even at low bitrates.

No-Reference Mesh Visual Quality Assessment via Ensemble of Convolutional Neural Networks and Compact Multi-Linear Pooling

Ilyass Abouelaziz (LRIT, Université Mohamed V, Rabat, Maroc), Aladine Chetouani (Laboratoire PRISME, Université d'Orléans), Mohamed El Hassouni (LRIT, Université Mohamed V, Rabat, Maroc)

Blind or No reference quality evaluation is a challenging issue since it is done without access to the original content. In this work, we propose a method based on deep learning for the mesh visual quality assessment without reference. For a given 3D model, we first compute its mesh saliency. Then, we extract views from the 3D mesh and the corresponding mesh saliency. After that, the views are split into small patches that are filtered using a saliency threshold. Only the salient patches are selected and used as input data. After that, three pre-trained deep convolutional neural networks are employed for feature learning: VGG, AlexNet, and ResNet. Each network is fine-tuned and produces a feature vector. The Compact Multi-linear Pooling (CMP) is used afterward to fuse the retrieved vectors into a global feature representation. Finally, fully connected layers followed by a regression module are used to estimate the quality score. Extensive experiments are executed on four mesh quality datasets and comparisons with existing methods demonstrate the effectiveness of our method in terms of correlation with subjective scores.

PCQM: A Full-Reference Quality Metric for Colored 3D Point Clouds

Gabriel Meynet, Yana Nehmé, Julie Digne and Guillaume Lavoué

3D point clouds constitute an emerging multimedia content, now used in a wide range of applications. The main drawback of this representation is the size of the data since typical point clouds may contain millions of points, usually associated with both geometry and color information. Consequently, a significant amount of work has been devoted to the efficient compression of this representation. Lossy compression leads to a degradation of the data and thus impacts the visual quality of the displayed content. In that context, predicting perceived visual quality computationally is essential for the optimization and evaluation of compression algorithms. In this paper, we introduce PCQM, a full-reference objective metric for visual quality assessment of 3D point clouds. The metric is an optimally-weighted linear combination of geometry-based and color-based features. We evaluate its performance on an open subjective dataset of colored point clouds compressed by several algorithms; the proposed quality assessment approach outperforms all previous metrics in terms of correlation with mean opinion scores.

An efficient representation of 3D buildings and its application to the evaluation of 3D city models

Oussama Ennafii, Arnaud Le Bris, Florent Lafarge, Clément Mallet

City modeling consists in building a semantic generalized model of the surface of urban objects. Most methods focus on 3D buildings with VHR overhead data (images and/or 3D point clouds). The literature abundantly addresses 3D mesh processing but frequently ignores the analysis of such models. This requires an efficient representation of 3D buildings. In particular, for them to be used in supervised learning tasks, such a representation should be scalable and transferable to various environments as only a few reference training instances would be available. In this paper, we propose two solutions that take into account the specificity of 3D urban models. They are based on graph kernels and ScatNet. They are then evaluated in the challenging framework of quality evaluation of building models. The latter is formulated as a supervised multilabel classification problem, where error labels are predicted at building level. The experiments show for both feature extraction strategy strong and complementary results (F-score > \SI{74}{\percent} for most labels). Transferability of the classification is also examined in order to assess the scalability of the evaluation process yielding very encouraging scores (F-score > 86% for most labels).

Date : 2020-06-02

Lieu : Visio-conférence


Thèmes scientifiques :
B - Image et Vision

Inscriptions closes à cette réunion.

Accéder au compte-rendu de cette réunion.

(c) GdR 720 ISIS - CNRS - 2011-2020.