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

03/29/2022
by   Soumava Kumar Roy, et al.
0

Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. Therefore, much of the recent attention has shifted towards semi and (or) weakly supervised learning. Generating an effective form of supervision with little annotations still poses major challenges in crowded scenes. However, since it is easy to observe a scene from multiple cameras, we propose to impose multi-view geometrical constraints by means of a differentiable triangulation and to use it as form of self-supervision during training when no labels are available. We therefore train a 2D pose estimator in such a way that its predictions correspond to the re-projection of the triangulated 3D one and train an auxiliary network on them to produce the final 3D poses. We complement the triangulation with a weighting mechanism that nullify the impact of noisy predictions caused by self-occlusion or occlusion from other subjects. Our experimental results on Human3.6M and MPI-INF-3DHP substantiate the significance of our weighting strategy where we obtain state-of-the-art results in the semi and weakly supervised learning setup. We also contribute a new multi-player sports dataset that features occlusion, and show the effectiveness of our algorithm over baseline triangulation methods.

READ FULL TEXT

page 17

page 18

research
06/04/2019

Semi- and Weakly-supervised Human Pose Estimation

For human pose estimation in still images, this paper proposes three sem...
research
04/09/2020

Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis

Camera captured human pose is an outcome of several sources of variation...
research
04/14/2021

Weakly But Deeply Supervised Occlusion-Reasoned Parametric Layouts

We propose an end-to-end network that takes a single perspective RGB ima...
research
04/03/2018

Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation

Modern 3D human pose estimation techniques rely on deep networks, which ...
research
05/14/2021

TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation from Video

Estimating 3D human poses from video is a challenging problem. The lack ...
research
09/13/2019

Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistency

We present a novel data-driven regularizer for weakly-supervised learnin...
research
10/20/2021

Self-Supervision and Spatial-Sequential Attention Based Loss for Multi-Person Pose Estimation

Bottom-up based multi-person pose estimation approaches use heatmaps wit...

Please sign up or login with your details

Forgot password? Click here to reset