Communities & Collections
Researchers & Labs
Titles
DGIST
LIBRARY
DGIST R&D
Detail View
Department of Electrical Engineering and Computer Science
Theses
Master
SegRig: Advanced Neural Rigging Network via 3D Semantic Segmentation
Junkyu Cho
Department of Electrical Engineering and Computer Science
Theses
Master
Citations
WEB OF SCIENCE
Citations
SCOPUS
Metadata Downloads
XML
Excel
Title
SegRig: Advanced Neural Rigging Network via 3D Semantic Segmentation
Alternative Title
3차원 의미적 분할을 이용한 고도화된 뉴럴 리깅 네트워크
DGIST Authors
Junkyu Cho
;
Daewon Seo
;
Gyeongsik Moon
Advisor
서대원
Co-Advisor(s)
Gyeongsik Moon
Issued Date
2025
Awarded Date
2025-02-01
Citation
Junkyu Cho. (2025). SegRig: Advanced Neural Rigging Network via 3D Semantic Segmentation. doi: 10.22677/THESIS.200000841174
Type
Thesis
Description
Mesh segmentation, Neural rigging, Joint prediction, Skeleton
Table Of Contents
I.Introduction 1
II.Related Works 4
2.1 Mesh Segmentation 4
2.2 Neural Rigging 5
III.Methods 8
3.1 Segmentation Attention 8
3.2 Displacement Loss 9
3.3 Attention Weighted Norm Loss 11
3.4 Total Rigging Prediction 12
IV.Experiments 14
4.1 Attention Ratio 14
4.2 Datasets 17
4.3 Out of Distribution 18
V.Conclusion 21
References 22
URI
http://hdl.handle.net/20.500.11750/58047
http://dgist.dcollection.net/common/orgView/200000841174
DOI
10.22677/THESIS.200000841174
Degree
Master
Department
Department of Electrical Engineering and Computer Science
Publisher
DGIST
Show Full Item Record
File Downloads
There are no files associated with this item.
공유
공유하기
Total Views & Downloads