MirrorNet: A Deep Reflective Approach to 2D Pose Estimation for Single-Person Images
-
- Nakatsuka Takayuki
- Waseda University
-
- Yoshii Kazuyoshi
- Kyoto University
-
- Koyama Yuki
- National Institute of Advanced Industrial Science and Technology (AIST)
-
- Fukayama Satoru
- National Institute of Advanced Industrial Science and Technology (AIST)
-
- Goto Masataka
- National Institute of Advanced Industrial Science and Technology (AIST)
-
- Morishima Shigeo
- Waseda Research Institute for Science and Engineering
Search this article
Abstract
<p>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.</p>
Journal
-
- Journal of Information Processing
-
Journal of Information Processing 29 (0), 406-423, 2021
Information Processing Society of Japan
- Tweet
Details 詳細情報について
-
- CRID
- 1390288060506441728
-
- NII Article ID
- 130008038621
- 170000184879
-
- NII Book ID
- AN00116647
-
- ISSN
- 18827764
- 18826652
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- IRDB
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed