VQ-HPS: Human pose and shape estimation in a vector-quantized latent space

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland

Detalles Bibliográficos
Autores: Fiche, Guénolé, Leglaive, Simon, Alameda-Pineda, Xavier, Agudo Martínez, Antonio|||0000-0001-6845-4998, Moreno-Noguer, Francesc
Tipo de recurso: capítulo de libro
Fecha de publicación:2024
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/425811
Acceso en línea:https://hdl.handle.net/2117/425811
https://dx.doi.org/10.1007/978-3-031-72943-0_27
Access Level:acceso abierto
Palabra clave:Human pose and shape estimation
Human mesh recovery
Vector quantized autoencoder
Transformers
Classificació INSPEC::Pattern recognition::Computer vision
Àrees temàtiques de la UPC::Informàtica::Automàtica i control
id ES_7ef9fb8c0289cd73ea6ddba49afd93ee
oai_identifier_str oai:upcommons.upc.edu:2117/425811
network_acronym_str ES
network_name_str España
repository_id_str
spelling VQ-HPS: Human pose and shape estimation in a vector-quantized latent spaceFiche, GuénoléLeglaive, SimonAlameda-Pineda, XavierAgudo Martínez, Antonio|||0000-0001-6845-4998Moreno-Noguer, FrancescHuman pose and shape estimationHuman mesh recoveryVector quantized autoencoderTransformersClassificació INSPEC::Pattern recognition::Computer visionÀrees temàtiques de la UPC::Informàtica::Automàtica i control© 2025 The Author(s), under exclusive license to Springer Nature SwitzerlandPrevious works on Human Pose and Shape Estimation (HPSE) from RGB images can be broadly categorized into two main groups: parametric and non-parametric approaches. Parametric techniques leverage a low-dimensional statistical body model for realistic results, whereas recent non-parametric methods achieve higher precision by directly regressing the 3D coordinates of the human body mesh. This work introduces a novel paradigm to address the HPSE problem, involving a low-dimensional discrete latent representation of the human mesh and framing HPSE as a classification task. Instead of predicting body model parameters or 3D vertex coordinates, we focus on predicting the proposed discrete latent representation, which can be decoded into a registered human mesh. This innovative paradigm offers two key advantages. Firstly, predicting a low-dimensional discrete representation confines our predictions to the space of anthropomorphic poses and shapes even when little training data is available. Secondly, by framing the problem as a classification task, we can harness the discriminative power inherent in neural networks. The proposed model, VQ-HPS, predicts the discrete latent representation of the mesh. The experimental results demonstrate that VQ-HPS outperforms the current state-of-the-art non-parametric approaches while yielding results as realistic as those produced by parametric methods when trained with little data. VQ-HPS also shows promising results when training on large-scale datasets, highlighting the significant potential of the classification approach for HPSE.This study is part of the EUR DIGISPORT project supported by the ANR within the framework of the PIA France 2030 (ANR-18-EURE-0022). This work was performed using HPC resources from the “Mésocentre” computing center of CentraleSupélec, École Normale Supérieure Paris-Saclay, and Université Paris-Saclay supported by CNRS and Région Île-de-France. This work has been partially supported by MIAI@Grenoble Alpes, (ANR-19-P3IA-0003).Peer ReviewedSpringer20242024-11-2920252025-03-07book parthttp://purl.org/coar/resource_type/c_3248AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/bookPartapplication/pdfhttps://hdl.handle.net/2117/425811https://dx.doi.org/10.1007/978-3-031-72943-0_27reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/4258112026-05-27T15:37:01Z
dc.title.none.fl_str_mv VQ-HPS: Human pose and shape estimation in a vector-quantized latent space
title VQ-HPS: Human pose and shape estimation in a vector-quantized latent space
spellingShingle VQ-HPS: Human pose and shape estimation in a vector-quantized latent space
Fiche, Guénolé
Human pose and shape estimation
Human mesh recovery
Vector quantized autoencoder
Transformers
Classificació INSPEC::Pattern recognition::Computer vision
Àrees temàtiques de la UPC::Informàtica::Automàtica i control
title_short VQ-HPS: Human pose and shape estimation in a vector-quantized latent space
title_full VQ-HPS: Human pose and shape estimation in a vector-quantized latent space
title_fullStr VQ-HPS: Human pose and shape estimation in a vector-quantized latent space
title_full_unstemmed VQ-HPS: Human pose and shape estimation in a vector-quantized latent space
title_sort VQ-HPS: Human pose and shape estimation in a vector-quantized latent space
dc.creator.none.fl_str_mv Fiche, Guénolé
Leglaive, Simon
Alameda-Pineda, Xavier
Agudo Martínez, Antonio|||0000-0001-6845-4998
Moreno-Noguer, Francesc
author Fiche, Guénolé
author_facet Fiche, Guénolé
Leglaive, Simon
Alameda-Pineda, Xavier
Agudo Martínez, Antonio|||0000-0001-6845-4998
Moreno-Noguer, Francesc
author_role author
author2 Leglaive, Simon
Alameda-Pineda, Xavier
Agudo Martínez, Antonio|||0000-0001-6845-4998
Moreno-Noguer, Francesc
author2_role author
author
author
author
dc.subject.none.fl_str_mv Human pose and shape estimation
Human mesh recovery
Vector quantized autoencoder
Transformers
Classificació INSPEC::Pattern recognition::Computer vision
Àrees temàtiques de la UPC::Informàtica::Automàtica i control
topic Human pose and shape estimation
Human mesh recovery
Vector quantized autoencoder
Transformers
Classificació INSPEC::Pattern recognition::Computer vision
Àrees temàtiques de la UPC::Informàtica::Automàtica i control
description © 2025 The Author(s), under exclusive license to Springer Nature Switzerland
publishDate 2024
dc.date.none.fl_str_mv 2024
2024-11-29
2025
2025-03-07
dc.type.none.fl_str_mv book part
http://purl.org/coar/resource_type/c_3248
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/bookPart
format bookPart
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/425811
https://dx.doi.org/10.1007/978-3-031-72943-0_27
url https://hdl.handle.net/2117/425811
https://dx.doi.org/10.1007/978-3-031-72943-0_27
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869411789654982656
score 15,812455

Similares en LA Referencia