AlignBodyNet: Deep Learning-Based Alignment of Non-Overlapping Partial Body Point Clouds From a Single Depth Camera

人工智能 计算机科学 计算机视觉 点云 点(几何) 深度学习 姿势 算法 数学 几何学
作者
Pengpeng Hu,Edmond S. L. Ho,Adrian Munteanu
出处
期刊:IEEE Transactions on Instrumentation and Measurement [Institute of Electrical and Electronics Engineers]
卷期号:72: 1-9 被引量:3
标识
DOI:10.1109/tim.2022.3222501
摘要

This article proposes a novel deep learning framework to generate omnidirectional 3-D point clouds of human bodies by registering the front- and back-facing partial scans captured by a single-depth camera. Our approach does not require calibration-assisting devices, canonical postures, nor does it make assumptions concerning an initial alignment or correspondences between the partial scans. This is achieved by factoring this challenging problem into: 1) building virtual correspondences for partial scans and 2) implicitly predicting the rigid transformation between the two partial scans via the predicted virtual correspondences. In this study, we regress the skinned multi-person linear model (SMPL) vertices from the two partial scans for building virtual correspondences. The main challenges are: 1) estimating the body shape and pose under clothing from single partially dressed body point clouds and 2) the predicted bodies from the front- and back-facing inputs required to be the same. We, thus, propose a novel deep neural network (DNN) dubbed AlignBodyNet that introduces shape-interrelated features and a shape-constraint loss for resolving this problem. We also provide a simple yet efficient method for generating real-world partial scans from complete models, which fills the gap in the lack of quantitative comparisons based on real-world data for various studies including partial registration, shape completion, and view synthesis. Experiments based on synthetic and real-world data show that our method achieves state-of-the-art performance in both objective and subjective terms.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
大模型应助欧阳月空采纳,获得10
4秒前
4秒前
ElvisWu完成签到,获得积分10
5秒前
5秒前
7秒前
moji发布了新的文献求助10
8秒前
Imp完成签到,获得积分10
10秒前
10秒前
11秒前
量子星尘发布了新的文献求助10
11秒前
12秒前
33发布了新的文献求助30
12秒前
彦卿完成签到 ,获得积分10
13秒前
思源应助赵清持采纳,获得10
14秒前
张雯思发布了新的文献求助10
15秒前
Orange应助Shrine采纳,获得10
16秒前
17秒前
卡卡罗特发布了新的文献求助10
17秒前
cdytjt完成签到,获得积分10
19秒前
22秒前
ding应助小田心采纳,获得10
22秒前
22秒前
22秒前
23秒前
23秒前
wwl发布了新的文献求助10
24秒前
鹏程万里完成签到,获得积分10
25秒前
星辰大海应助li采纳,获得10
26秒前
chasikan发布了新的文献求助30
27秒前
cxy发布了新的文献求助10
28秒前
幸福大白发布了新的文献求助10
29秒前
大个应助贾克斯采纳,获得10
31秒前
过时的画板完成签到,获得积分10
31秒前
大气小蘑菇完成签到,获得积分10
34秒前
35秒前
小田心发布了新的文献求助10
41秒前
千跃举报求助违规成功
41秒前
whatever举报求助违规成功
41秒前
wdy111举报求助违规成功
41秒前
41秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989406
求助须知:如何正确求助?哪些是违规求助? 3531522
关于积分的说明 11254187
捐赠科研通 3270174
什么是DOI,文献DOI怎么找? 1804901
邀请新用户注册赠送积分活动 882105
科研通“疑难数据库(出版商)”最低求助积分说明 809174