Ir al contenido (pulsa Retorno)

Universitat Politècnica de Catalunya

    • Català
    • Castellano
    • English
    • LoginRegisterLog in (no UPC users)
  • mailContact Us
  • world English 
    • Català
    • Castellano
    • English
  • userLogin   
      LoginRegisterLog in (no UPC users)

UPCommons. Global access to UPC knowledge

58.848 UPC E-Prints
You are here:
View Item 
  •   DSpace Home
  • E-prints
  • Instituts de recerca
  • IRI - Institut de Robòtica i Informàtica Industrial, CSIC-UPC
  • Ponències/Comunicacions de congressos
  • View Item
  •   DSpace Home
  • E-prints
  • Instituts de recerca
  • IRI - Institut de Robòtica i Informàtica Industrial, CSIC-UPC
  • Ponències/Comunicacions de congressos
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Human motion prediction via spatio-temporal inpainting

Thumbnail
View/Open
2259-Human-Motion-Prediction-via-Spatio-Temporal-Inpainting.pdf (697,3Kb)
Share:
 
 
10.1109/ICCV.2019.00723
 
  View Usage Statistics
Cita com:
hdl:2117/187445

Show full item record
Hernández Ruiz, Alejandro JoséMés informació
Gall, Juergen
Moreno-Noguer, FrancescMés informació
Document typeConference report
Defense date2019
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Rights accessOpen Access
Attribution-NonCommercial-NoDerivs 3.0 Spain
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain
Abstract
We propose a Generative Adversarial Network (GAN) to forecast 3D human motion given a sequence of past 3D skeleton poses. While recent GANs have shown promising results, they can only forecast plausible motion over relatively short periods of time (few hundred milliseconds) and typically ignore the absolute position of the skeleton w.r.t. the camera. Our scheme provides long term predictions (two seconds or more) for both the body pose and its absolute position. Our approach builds upon three main contributions. First, we represent the data using a spatio-temporal tensor of 3D skeleton coordinates which allows formulating the prediction problem as an inpainting one, for which GANs work particularly well. Secondly, we design an architecture to learn the joint distribution of body poses and global motion, capable to hypothesize large chunks of the input 3D tensor with missing data. And finally, we argue that the L2 metric, considered so far by most approaches, fails to capture the actual distribution of long-term human motion. We propose two alternative metrics, based on the distribution of frequencies, that are able to capture more realistic motion patterns. Extensive experiments demonstrate our approach to significantly improve the state of the art, while also handling situations in which past observations are corrupted by occlusions, noise and missing frames.
Description
© 2019 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
CitationHernandez, A.; Gall, J.; Moreno-Noguer, F. Human motion prediction via spatio-temporal inpainting. A: IEEE International Conference on Computer Vision. "2019 IEEE/CVF International Conference on Computer Vision (ICCV)". Institute of Electrical and Electronics Engineers (IEEE), 2019, p. 7133-7142. 
URIhttp://hdl.handle.net/2117/187445
DOI10.1109/ICCV.2019.00723
ISBN978-1-7281-4803-8
Publisher versionhttps://ieeexplore.ieee.org/document/9008530
Collections
  • IRI - Institut de Robòtica i Informàtica Industrial, CSIC-UPC - Ponències/Comunicacions de congressos [463]
  • ROBiri - Grup de Robòtica de l'IRI - Ponències/Comunicacions de congressos [219]
  • Doctorat en Automàtica, Robòtica i Visió - Ponències/Comunicacions de congressos [120]
Share:
 
  View Usage Statistics

Show full item record

FilesDescriptionSizeFormatView
2259-Human-Moti ... io-Temporal-Inpainting.pdf697,3KbPDFView/Open

Browse

This CollectionBy Issue DateAuthorsOther contributionsTitlesSubjectsThis repositoryCommunities & CollectionsBy Issue DateAuthorsOther contributionsTitlesSubjects

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

info.biblioteques@upc.edu

  • About This Repository
  • Contact Us
  • Send Feedback
  • Inici de la pàgina