View-Invariant Probabilistic Embedding for Human Pose

12/02/2019
by   Jennifer J. Sun, et al.
5

Depictions of similar human body configurations can vary with changing viewpoints. Using only 2D information, we would like to enable vision algorithms to recognize similarity in human body poses across multiple views. This ability is useful for analyzing body movements and human behaviors in images and videos. In this paper, we propose an approach for learning a compact view-invariant embedding space from 2D joint keypoints alone, without explicitly predicting 3D poses. Since 2D poses are projected from 3D space, they have an inherent ambiguity, which is difficult to represent through a deterministic mapping. Hence, we use probabilistic embeddings to model this input uncertainty. Experimental results show that our embedding model achieves higher accuracy when retrieving similar poses across different camera views, in comparison with 2D-to-3D pose lifting models. The results also suggest that our model is able to generalize across datasets, and our embedding variance correlates with input pose ambiguity.

READ FULL TEXT

page 7

page 17

research
10/23/2020

View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose

Recognition of human poses and activities is crucial for autonomous syst...
research
01/30/2019

View Invariant 3D Human Pose Estimation

The recent success of deep networks has significantly advanced 3D human ...
research
04/19/2022

VCoach: A Customizable Visualization and Analysis System for Video-based Running Coaching

Videos are accessible media for analyzing sports postures and providing ...
research
08/01/2023

Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstruction

While 3D body reconstruction methods have made remarkable progress recen...
research
01/06/2022

Enhancing Egocentric 3D Pose Estimation with Third Person Views

In this paper, we propose a novel approach to enhance the 3D body pose e...
research
10/17/2017

Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation

In this paper, we propose a pose grammar to tackle the problem of 3D hum...
research
07/18/2020

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

Human poses that are rare or unseen in a training set are challenging fo...

Please sign up or login with your details

Forgot password? Click here to reset