Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Purkrabek, Miroslav, Matas, Jiri
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909254580961280
author Purkrabek, Miroslav
Matas, Jiri
author_facet Purkrabek, Miroslav
Matas, Jiri
contents Methods and datasets for human pose estimation focus predominantly on side- and front-view scenarios. We overcome the limitation by leveraging synthetic data and introduce RePoGen (RarE POses GENerator), an SMPL-based method for generating synthetic humans with comprehensive control over pose and view. Experiments on top-view datasets and a new dataset of real images with diverse poses show that adding the RePoGen data to the COCO dataset outperforms previous approaches to top- and bottom-view pose estimation without harming performance on common views. An ablation study shows that anatomical plausibility, a property prior research focused on, is not a prerequisite for effective performance. The introduced dataset and the corresponding code are available on https://mirapurkrabek.github.io/RePoGen-paper/ .
format Preprint
id arxiv_https___arxiv_org_abs_2307_06737
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Data
Purkrabek, Miroslav
Matas, Jiri
Computer Vision and Pattern Recognition
Methods and datasets for human pose estimation focus predominantly on side- and front-view scenarios. We overcome the limitation by leveraging synthetic data and introduce RePoGen (RarE POses GENerator), an SMPL-based method for generating synthetic humans with comprehensive control over pose and view. Experiments on top-view datasets and a new dataset of real images with diverse poses show that adding the RePoGen data to the COCO dataset outperforms previous approaches to top- and bottom-view pose estimation without harming performance on common views. An ablation study shows that anatomical plausibility, a property prior research focused on, is not a prerequisite for effective performance. The introduced dataset and the corresponding code are available on https://mirapurkrabek.github.io/RePoGen-paper/ .
title Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Data
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2307.06737