PNO: Personalized Network Optimization for Human Pose and Shape Reconstruction

  • Zhijie Cao
  • , Min Wang
  • , Shanyan Guan
  • , Wentao Liu
  • , Chen Qian
  • , Lizhuang Ma*
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Most previous human pose and shape reconstruction methods focus on the generalization ability and learn a prior of the general pose and shape, however the personalized features are often ignored. We argue that the personalized features such as appearance and body shape are always consistent for the specific person and can further improve the accuracy. In this paper, we propose a Personalized Network Optimization (PNO) method to maintain both generalization and personality for human pose and shape reconstruction. The general trained network is adapted to the personalized network by optimizing with only a few unlabeled video frames of the target person. Moreover, we specially propose geometry-aware temporal constraints that help the network better exploit the geometry knowledge of the target person. In order to prove the effectiveness of PNO, we re-design the benchmark of pose and shape reconstruction to test on each person independently. Experiments show that our method achieve the state-of-the-art results in both 3DPW and MPI-INF-3DHP datasets.

Original languageEnglish
Title of host publicationArtificial Neural Networks and Machine Learning – ICANN 2021 - 30th International Conference on Artificial Neural Networks, Proceedings
EditorsIgor Farkaš, Paolo Masulli, Sebastian Otte, Stefan Wermter
PublisherSpringer Science and Business Media Deutschland GmbH
Pages356-367
Number of pages12
ISBN (Print)9783030863647
DOIs
StatePublished - 2021
Event30th International Conference on Artificial Neural Networks, ICANN 2021 - Virtual, Online, Slovakia
Duration: 14 Sep 202117 Sep 2021

Publication series

NameLecture Notes in Computer Science
Volume12893 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference30th International Conference on Artificial Neural Networks, ICANN 2021
Country/TerritorySlovakia
CityVirtual, Online
Period14/09/2117/09/21

Keywords

  • Human mesh recovery
  • Human pose and shape reconstruction
  • Personalized Network Optimization

Fingerprint

Dive into the research topics of 'PNO: Personalized Network Optimization for Human Pose and Shape Reconstruction'. Together they form a unique fingerprint.

Cite this