Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation

04/03/2018
by   Helge Rhodin, et al.
0

Modern 3D human pose estimation techniques rely on deep networks, which require large amounts of training data. While weakly-supervised methods require less supervision, by utilizing 2D poses or multi-view imagery without annotations, they still need a sufficiently large set of samples with 3D annotations for learning to succeed. In this paper, we propose to overcome this problem by learning a geometry-aware body representation from multi-view images without annotations. To this end, we use an encoder-decoder that predicts an image from one viewpoint given an image from another viewpoint. Because this representation encodes 3D geometry, using it in a semi-supervised setting makes it easier to learn a mapping from it to 3D human pose. As evidenced by our experiments, our approach significantly outperforms fully-supervised methods given the same amount of labeled data, and improves over other semi-supervised methods while using as little as 1

READ FULL TEXT

page 11

page 12

page 13

page 14

research
03/21/2019

Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation

Recent studies have shown remarkable advances in 3D human pose estimatio...
research
04/02/2021

Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generation

There is a growing interest in developing computer vision methods that c...
research
11/25/2017

Structure-Aware and Temporally Coherent 3D Human Pose Estimation

Deep learning methods for 3D human pose estimation from RGB images requi...
research
07/24/2018

Learning Human Poses from Actions

We consider the task of learning to estimate human pose in still images....
research
03/29/2022

On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation

Supervised approaches to 3D pose estimation from single images are remar...
research
03/07/2022

Weakly Supervised Learning of Keypoints for 6D Object Pose Estimation

State-of-the-art approaches for 6D object pose estimation require large ...
research
12/29/2022

Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats

Deep learning-based 3D human pose estimation performs best when trained ...

Please sign up or login with your details

Forgot password? Click here to reset