Mirrornet: A deep reflective approach to 2d pose estimation for single-person images

Takayuki Nakatsuka*, Kazuyoshi Yoshii, Yuki Koyama, Satoru Fukayama, Masataka Goto, Shigeo Morishima

*この研究の対応する著者

研究成果: Article査読

抄録

This paper proposes a statistical approach to 2D pose estimation from human images. The main problems with the standard supervised approach, which is based on a deep recognition (image-to-pose) model, are that it often yields anatomically implausible poses, and its performance is limited by the amount of paired data. To solve these problems, we propose a semi-supervised method that can make effective use of images with and without pose annotations. Specifically, we formulate a hierarchical generative model of poses and images by integrating a deep generative model of poses from pose features with that of images from poses and image features. We then introduce a deep recognition model that infers poses from images. Given images as observed data, these models can be trained jointly in a hierarchical variational autoencoding (image-to-pose-to-feature-to-pose-to-image) manner. The results of experiments show that the proposed reflective architecture makes estimated poses anatomically plausible, and the pose estimation performance is improved by integrating the recognition and generative models and also by feeding non-annotated images.

本文言語English
ページ(範囲)406-423
ページ数18
ジャーナルJournal of information processing
29
DOI
出版ステータスPublished - 2021 5

ASJC Scopus subject areas

  • コンピュータ サイエンス(全般)

フィンガープリント

「Mirrornet: A deep reflective approach to 2d pose estimation for single-person images」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル