Saved in:
Bibliographic Details
Main Authors: Yu, Jingrui, Nandi, Dipankar, Seidel, Roman, Hirtz, Gangolf
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.18196
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913327097053184
author Yu, Jingrui
Nandi, Dipankar
Seidel, Roman
Hirtz, Gangolf
author_facet Yu, Jingrui
Nandi, Dipankar
Seidel, Roman
Hirtz, Gangolf
contents Human pose estimation (HPE) in the top-view using fisheye cameras presents a promising and innovative application domain. However, the availability of datasets capturing this viewpoint is extremely limited, especially those with high-quality 2D and 3D keypoint annotations. Addressing this gap, we leverage the capabilities of Neural Radiance Fields (NeRF) technique to establish a comprehensive pipeline for generating human pose datasets from existing 2D and 3D datasets, specifically tailored for the top-view fisheye perspective. Through this pipeline, we create a novel dataset NToP570K (NeRF-powered Top-view human Pose dataset for fisheye cameras with over 570 thousand images), and conduct an extensive evaluation of its efficacy in enhancing neural networks for 2D and 3D top-view human pose estimation. A pretrained ViTPose-B model achieves an improvement in AP of 33.3 % on our validation set for 2D HPE after finetuning on our training set. A similarly finetuned HybrIK-Transformer model gains 53.7 mm reduction in PA-MPJPE for 3D HPE on the validation set.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18196
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Images
Yu, Jingrui
Nandi, Dipankar
Seidel, Roman
Hirtz, Gangolf
Computer Vision and Pattern Recognition
Graphics
Human pose estimation (HPE) in the top-view using fisheye cameras presents a promising and innovative application domain. However, the availability of datasets capturing this viewpoint is extremely limited, especially those with high-quality 2D and 3D keypoint annotations. Addressing this gap, we leverage the capabilities of Neural Radiance Fields (NeRF) technique to establish a comprehensive pipeline for generating human pose datasets from existing 2D and 3D datasets, specifically tailored for the top-view fisheye perspective. Through this pipeline, we create a novel dataset NToP570K (NeRF-powered Top-view human Pose dataset for fisheye cameras with over 570 thousand images), and conduct an extensive evaluation of its efficacy in enhancing neural networks for 2D and 3D top-view human pose estimation. A pretrained ViTPose-B model achieves an improvement in AP of 33.3 % on our validation set for 2D HPE after finetuning on our training set. A similarly finetuned HybrIK-Transformer model gains 53.7 mm reduction in PA-MPJPE for 3D HPE on the validation set.
title NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Images
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2402.18196