Saved in:
Bibliographic Details
Main Authors: Lee, Hyunsoo, Jeon, Daeum, Oh, Hyeokjae
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.10321
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908704992919552
author Lee, Hyunsoo
Jeon, Daeum
Oh, Hyeokjae
author_facet Lee, Hyunsoo
Jeon, Daeum
Oh, Hyeokjae
contents We propose a novel generative approach for 3D human pose estimation. 3D human pose estimation poses several key challenges due to the complex geometry of the human body, self-occluding joints, and the requirement for large-scale real-world motion datasets. To address these challenges, we introduce Point2Pose, a framework that effectively models the distribution of human poses conditioned on sequential point cloud and pose history. Specifically, we employ a spatio-temporal point cloud encoder and a pose feature encoder to extract joint-wise features, followed by an attention-based generative regressor. Additionally, we present a large-scale indoor dataset MVPose3D, which contains multiple modalities, including IMU data of non-trivial human motions, dense multi-view point clouds, and RGB images. Experimental results show that the proposed method outperforms the baseline models, demonstrating its superior performance across various datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10321
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Point2Pose: A Generative Framework for 3D Human Pose Estimation with Multi-View Point Cloud Dataset
Lee, Hyunsoo
Jeon, Daeum
Oh, Hyeokjae
Computer Vision and Pattern Recognition
We propose a novel generative approach for 3D human pose estimation. 3D human pose estimation poses several key challenges due to the complex geometry of the human body, self-occluding joints, and the requirement for large-scale real-world motion datasets. To address these challenges, we introduce Point2Pose, a framework that effectively models the distribution of human poses conditioned on sequential point cloud and pose history. Specifically, we employ a spatio-temporal point cloud encoder and a pose feature encoder to extract joint-wise features, followed by an attention-based generative regressor. Additionally, we present a large-scale indoor dataset MVPose3D, which contains multiple modalities, including IMU data of non-trivial human motions, dense multi-view point clouds, and RGB images. Experimental results show that the proposed method outperforms the baseline models, demonstrating its superior performance across various datasets.
title Point2Pose: A Generative Framework for 3D Human Pose Estimation with Multi-View Point Cloud Dataset
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.10321