Modeling 3D articulated motions with conformal geometry videos (CGVs)

3D articulated motions are widely used in entertainment, sports, military, and medical applications. Among various techniques for modeling 3D motions, geometry videos (GVs) are a compact representation in that each frame is parameterized to a 2D domain, which captures the 3D geometry (x, y, z) to a...

Full description

Saved in:
Bibliographic Details
Main Authors: QUYNH, Dao T. P., HE, Ying, CHEN, Xiaoming, XIA, Jiazhi, SUN, Qian, HOI, Steven C. H.
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2011
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/4178
https://ink.library.smu.edu.sg/context/sis_research/article/5181/viewcontent/Modeling_3D_MM_2011.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-5181
record_format dspace
spelling sg-smu-ink.sis_research-51812019-05-31T08:02:40Z Modeling 3D articulated motions with conformal geometry videos (CGVs) QUYNH, Dao T. P. HE, Ying CHEN, Xiaoming XIA, Jiazhi SUN, Qian HOI, Steven C. H. 3D articulated motions are widely used in entertainment, sports, military, and medical applications. Among various techniques for modeling 3D motions, geometry videos (GVs) are a compact representation in that each frame is parameterized to a 2D domain, which captures the 3D geometry (x, y, z) to a pixel (r, g, b) in the image domain. As a result, the widely studied image/video processing techniques can be directly borrowed for 3D motion. This paper presents conformal geometry videos (CGVs), a novel extension of the traditional geometry videos by taking into the consideration of the isometric nature of 3D articulated motions. We prove that the 3D articulated motion can be uniquely (up to rigid motion) represented by (λ,H), where λ is the conformal factor characterizing the intrinsic property of the 3D motion, and H the mean curvature characterizing the extrinsic feature (i.e., embedding or appearance). Furthermore, the conformal factor λ is pose-invariant. Thus, in sharp contrast to the GVs which capture 3D motion by three channels, CGVs take only one channel of mean curvature H and the first frame of the conformal factor λ, i.e., approximately 1/3 the storage of the GVs. In addition, CGVs have strong spatial and temporal coherence, which favors various well studied video compression techniques. Thus, CGVs can be highly compressed by using the state-of-the-art video compression techniques, such as H.264/AVC. Our experimental results on real-world 3D motions show that CGVs are a highly compact representation for 3D articulated motions, i.e., given CGVs and GVs of the same file size, CGVs show much better visual quality than GVs. 2011-12-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4178 info:doi/10.1145/2072298.2072349 https://ink.library.smu.edu.sg/context/sis_research/article/5181/viewcontent/Modeling_3D_MM_2011.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University 3D articulated motion Conformal parameterization Conformal geometry videos Geometry videos Deformable objects Isometric transformation H.264/AVC Video compression Databases and Information Systems Numerical Analysis and Computation
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic 3D articulated motion
Conformal parameterization
Conformal geometry videos
Geometry videos
Deformable objects
Isometric transformation
H.264/AVC
Video compression
Databases and Information Systems
Numerical Analysis and Computation
spellingShingle 3D articulated motion
Conformal parameterization
Conformal geometry videos
Geometry videos
Deformable objects
Isometric transformation
H.264/AVC
Video compression
Databases and Information Systems
Numerical Analysis and Computation
QUYNH, Dao T. P.
HE, Ying
CHEN, Xiaoming
XIA, Jiazhi
SUN, Qian
HOI, Steven C. H.
Modeling 3D articulated motions with conformal geometry videos (CGVs)
description 3D articulated motions are widely used in entertainment, sports, military, and medical applications. Among various techniques for modeling 3D motions, geometry videos (GVs) are a compact representation in that each frame is parameterized to a 2D domain, which captures the 3D geometry (x, y, z) to a pixel (r, g, b) in the image domain. As a result, the widely studied image/video processing techniques can be directly borrowed for 3D motion. This paper presents conformal geometry videos (CGVs), a novel extension of the traditional geometry videos by taking into the consideration of the isometric nature of 3D articulated motions. We prove that the 3D articulated motion can be uniquely (up to rigid motion) represented by (λ,H), where λ is the conformal factor characterizing the intrinsic property of the 3D motion, and H the mean curvature characterizing the extrinsic feature (i.e., embedding or appearance). Furthermore, the conformal factor λ is pose-invariant. Thus, in sharp contrast to the GVs which capture 3D motion by three channels, CGVs take only one channel of mean curvature H and the first frame of the conformal factor λ, i.e., approximately 1/3 the storage of the GVs. In addition, CGVs have strong spatial and temporal coherence, which favors various well studied video compression techniques. Thus, CGVs can be highly compressed by using the state-of-the-art video compression techniques, such as H.264/AVC. Our experimental results on real-world 3D motions show that CGVs are a highly compact representation for 3D articulated motions, i.e., given CGVs and GVs of the same file size, CGVs show much better visual quality than GVs.
format text
author QUYNH, Dao T. P.
HE, Ying
CHEN, Xiaoming
XIA, Jiazhi
SUN, Qian
HOI, Steven C. H.
author_facet QUYNH, Dao T. P.
HE, Ying
CHEN, Xiaoming
XIA, Jiazhi
SUN, Qian
HOI, Steven C. H.
author_sort QUYNH, Dao T. P.
title Modeling 3D articulated motions with conformal geometry videos (CGVs)
title_short Modeling 3D articulated motions with conformal geometry videos (CGVs)
title_full Modeling 3D articulated motions with conformal geometry videos (CGVs)
title_fullStr Modeling 3D articulated motions with conformal geometry videos (CGVs)
title_full_unstemmed Modeling 3D articulated motions with conformal geometry videos (CGVs)
title_sort modeling 3d articulated motions with conformal geometry videos (cgvs)
publisher Institutional Knowledge at Singapore Management University
publishDate 2011
url https://ink.library.smu.edu.sg/sis_research/4178
https://ink.library.smu.edu.sg/context/sis_research/article/5181/viewcontent/Modeling_3D_MM_2011.pdf
_version_ 1770574395017789440