Ir al contenido (pulsa Retorno)

Universitat Politècnica de Catalunya

    • Català
    • Castellano
    • English
    • AccederRegistro (usuarios no UPC)Acceder (usuarios no UPC)
  • mailContacto
  • world Castellano 
    • Català
    • Castellano
    • English
  • userInicia sesión   
      AccederRegistro (usuarios no UPC)Acceder (usuarios no UPC)

UPCommons. Portal de acceso abierto al conocimiento de la UPC

Banner header
61.695 E-prints UPC
You are here:
Ver ítem 
  •   UPCommons
  • E-prints
  • Grups de recerca
  • ROBiri - Grup de Robòtica de l'IRI
  • Articles de revista
  • Ver ítem
  •   UPCommons
  • E-prints
  • Grups de recerca
  • ROBiri - Grup de Robòtica de l'IRI
  • Articles de revista
  • Ver ítem
JavaScript is disabled for your browser. Some features of this site may not work without it.

3D Human pose, shape and texture from low-resolution images and videos

Thumbnail
Ver/Abrir
2506-3D-Human-Pose,-Shape-and-Texture-from-Low-Resolution-Images-and-Videos.pdf (3,584Mb)
 
10.1109/TPAMI.2021.3070002
 
  Ver Estadísticas de uso
  Estadisticas de LA Referencia / Recolecta
Cita com:
hdl:2117/367104

Mostrar el registro completo del ítem
Xu, Xiangyu
Chen, Hao
Moreno-Noguer, FrancescMés informació
Jeni, Lázló
De La Torre, Fernando
Tipo de documentoArtículo
Fecha de publicación2022
Condiciones de accesoAcceso abierto
Todos los derechos reservados. Esta obra está protegida por los derechos de propiedad intelectual e industrial. Sin perjuicio de las exenciones legales existentes, queda prohibida su reproducción, distribución, comunicación pública o transformación sin la autorización del titular de los derechos
Resumen
3D human pose and shape estimation from monocular images has been an active research area in computer vision. Existing deep learning methods for this task rely on high-resolution input, which however, is not always available in many scenarios such as video surveillance and sports broadcasting. Two common approaches to deal with low-resolution images are applying super-resolution techniques to the input, which may result in unpleasant artifacts, or simply training one model for each resolution, which is impractical in many realistic applications. To address the above issues, this paper proposes a novel algorithm called RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme. The proposed method is able to learn 3D body pose and shape across different resolutions with one single model. The self-supervision loss enforces scale-consistency of the output, and the contrastive learning scheme enforces scale-consistency of the deep features. We show that both these new losses provide robustness when learning in a weakly-supervised manner. Moreover, we extend the RSC-Net to handle low-resolution videos and apply it to reconstruct textured 3D pedestrians from low-resolution input. Extensive experiments demonstrate that the RSC-Net can achieve consistently better results than the state-of-the-art methods for challenging low-resolution images.
Descripción
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
CitaciónXu, X. [et al.]. 3D Human pose, shape and texture from low-resolution images and videos. "IEEE transactions on pattern analysis and machine intelligence", 2022, p. 1. 
URIhttp://hdl.handle.net/2117/367104
DOI10.1109/TPAMI.2021.3070002
ISSN0162-8828
Versión del editorhttps://ieeexplore.ieee.org/document/9392295
Colecciones
  • ROBiri - Grup de Robòtica de l'IRI - Articles de revista [148]
  Ver Estadísticas de uso

Mostrar el registro completo del ítem

FicherosDescripciónTamañoFormatoVer
2506-3D-Human-P ... tion-Images-and-Videos.pdf3,584MbPDFVer/Abrir

Listar

Esta colecciónPor fechaAutoresOtras contribucionesTítulosMateriasEste repositorioComunidades & coleccionesPor fechaAutoresOtras contribucionesTítulosMaterias

© UPC Obrir en finestra nova . Servei de Biblioteques, Publicacions i Arxius

info.biblioteques@upc.edu

  • Sobre esta web
  • Contacto
  • Sugerencias
  • Configuración de privacidad
  • Inici de la pàgina