PanopTOP: a framework for generating viewpoint-invariant human pose estimation datasets

Human pose estimation (HPE) from RGB and depth images has recently experienced a push for viewpoint-invariant and scale-invariant pose retrieval methods. Current methods fail to generalize to unconventional viewpoints due to the lack of viewpoint-invariant data at training time. Existing datasets do...

Full description

Saved in:
Bibliographic Details
Main Authors: Garau, Nicola, Martinelli, Giulia, Brodka, Piotr, Bisagno, Niccolo, Conci, Nicola
Format: Conference Proceeding
Language:English
Subjects:
Codes
Computer vision
Conferences
Manifolds
Pose estimation
Three-dimensional displays
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Human pose estimation (HPE) from RGB and depth images has recently experienced a push for viewpoint-invariant and scale-invariant pose retrieval methods. Current methods fail to generalize to unconventional viewpoints due to the lack of viewpoint-invariant data at training time. Existing datasets do not provide multiple-viewpoint observations and mostly focus on frontal views. In this work, we introduce PanopTOP, a fully automatic framework for the generation of semi-synthetic RGB and depth samples with 2D and 3D ground truth of pedestrian poses from multiple arbitrary viewpoints. Starting from the Panoptic Dataset [15], we use the PanopTOP framework to generate the PanopTOP31K dataset, consisting of 31K images from 23 different subjects recorded from diverse and challenging viewpoints, also including the top-view. Finally, we provide baseline results and cross-validation tests for our dataset, demonstrating how it is possible to generalize from the semi-synthetic to the real-world domain. The dataset and the code will be made publicly available upon acceptance.
ISSN:2473-9944
DOI:10.1109/ICCVW54120.2021.00031