Unsupervised Learning on Monocular Videos for 3D Human Pose Estimation

12/02/2020
by   Sina Honari, et al.
3

In this paper, we introduce an unsupervised feature extraction method that exploits contrastive self-supervised (CSS) learning to extract rich latent vectors from single-view videos. Instead of simply treating the latent features of nearby frames as positive pairs and those of temporally-distant ones as negative pairs as in other CSS approaches, we explicitly separate each latent vector into a time-variant component and a time-invariant one. We then show that applying CSS only to the time-variant features, while also reconstructing the input and encouraging a gradual transition between nearby and away features yields a rich latent space, well-suited for human pose estimation. Our approach outperforms other unsupervised single-view methods and match the performance of multi-view techniques.

READ FULL TEXT

page 2

page 3

page 8

page 11

page 12

page 13

page 14

page 15

research
11/23/2022

Unsupervised 3D Keypoint Estimation with Multi-View Geometry

Given enough annotated training data, 3D human pose estimation models ca...
research
04/05/2022

Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation

Available 3D human pose estimation approaches leverage different forms o...
research
04/09/2019

Unsupervised 3D Pose Estimation with Geometric Self-Supervision

We present an unsupervised learning approach to recover 3D human pose fr...
research
01/07/2020

Deep Reinforcement Learning for Active Human Pose Estimation

Most 3d human pose estimation methods assume that input – be it images o...
research
08/14/2019

3D Human Pose Estimation under limited supervision using Metric Learning

Estimating 3D human pose from monocular images demands large amounts of ...
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
03/07/2023

A Light-Weight Contrastive Approach for Aligning Human Pose Sequences

We present a simple unsupervised method for learning an encoder mapping ...

Please sign up or login with your details

Forgot password? Click here to reset