Optimizing 3D Clothing Models for VR: A Deep Learning Approach to Triangle Count Reduction

被引：0

作者：

Doungtap, Surasachai ^{[1
]}

Phanichraksaphong, Varinya ^{[1
]}

Wang, Jenq-Haur ^{[2
]}

机构：

[1] Natl Taipei Univ Technol, Int Grad Program Elect Engn & Comp Sci, Taipei 10608, Taiwan

[2] Natl Taipei Univ Technol, Dept Comp Sci & Informat Engn, Taipei 10608, Taiwan

来源：

2024 11TH INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS-TAIWAN, ICCE-TAIWAN 2024 | 2024年

关键词：

3D Reconstruction; Deep Learning; Topology Optimization; Virtual Reality; Triangle Count Reduction;

D O I：

10.1109/ICCE-Taiwan62264.2024.10674064

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This study presents a deep learning framework optimizing 3D clothing models for VR, using a CNN to significantly reduce the triangle count of models from DeepFashion3D and CAP-UDF datasets. Achieving a balance between efficiency and detail, it cuts triangle count from over 160,000 to below 4,000, maintaining high DPI. The approach automates optimization, promising scalability and efficiency in VR fashion, setting a foundation for future 3D content development, enhancing virtual garment realism and interactivity.

引用

页码：733 / 734

页数：2

共 50 条

[1] Tangible Organs - Introducing 3D Printed Organ Models with VR to Interact with Medical 3D Models
Reinschluessel, Anke, V
Muender, Thomas
Uslar, Verena
Weyhe, Dirk
Schenk, Andrea
Malaka, Rainer
CHI EA '19 EXTENDED ABSTRACTS: EXTENDED ABSTRACTS OF THE 2019 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS, 2019,
[2] DEEP LEARNING FOR 3D BUILDING RECONSTRUCTION: A REVIEW
Buyukdemircioglu, Mehmet
Kocaman, Sultan
Kada, Martin
XXIV ISPRS CONGRESS IMAGING TODAY, FORESEEING TOMORROW, COMMISSION II, 2022, 43-B2 : 359 - 366
[3] A deep learning approach for predicting the architecture of 3D textile fabrics
Koptelov, Anatoly
Thompson, Adam
Hallett, Stephen R.
El Said, Bassam
MATERIALS & DESIGN, 2024, 239
[4] Deep Learning for Quality Control of Subcortical Brain 3D Shape Models
Petrov, Dmitry
Gutman, Boris A.
Kuznetsov, Egor
Ching, Christopher R. K.
Alpert, Kathryn
Zavaliangos-Petropulu, Artemis
Isaev, Dmitry
Turner, Jessica A.
Van Erp, Theo G. M.
Wang, Lei
Schmaal, Lianne
Veltman, Dick
Thompson, Paul M.
SHAPE IN MEDICAL IMAGING, SHAPEMI 2018, 2018, 11167 : 268 - 276
[5] GENERALIZATION PROPERTIES OF GEOMETRIC 3D DEEP LEARNING MODELS FOR MEDICAL SEGMENTATION
Lebrat, Leo
Cruz, Rodrigo Santa
Dorent, Reuben
Yaksic, Javier Urriola
Pagnozzi, Alex
Belous, Gregg
Bourgeat, Pierrick
Fripp, Jurgen
Fookes, Clinton
Salvado, Olivier
2023 IEEE 20TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, ISBI, 2023,
[6] COMBINING VISIBILITY ANALYSIS AND DEEP LEARNING FOR REFINEMENT OF SEMANTIC 3D BUILDING MODELS BY CONFLICT CLASSIFICATION
Wysocki, O.
Grilli, E.
Hoegner, L.
Stilla, U.
17TH 3D GEOINFO CONFERENCE, 2022, 10-4 (W2): : 289 - 296
[7] A Deep Learning Architecture for 3D Mapping Urban Landscapes
Rodriguez-Santiago, Armando Levid
Arias-Aguilar, Jose Anibal
Takemura, Hiroshi
Petrilli-Barcelo, Alberto Elias
APPLIED SCIENCES-BASEL, 2021, 11 (23):
[8] DETECTION OF SINGULARITIES IN FINITE ELEMENT SIMULATIONS: A 3D DEEP LEARNING APPROACH
Bickel, Sebastian
Goetz, Stefan
Wartzack, Sandro
PROCEEDINGS OF ASME 2023 INTERNATIONAL DESIGN ENGINEERING TECHNICAL CONFERENCES AND COMPUTERS AND INFORMATION IN ENGINEERING CONFERENCE, IDETC-CIE2023, VOL 2, 2023,
[9] Liver Tumors Segmentation Using 3D SegNet Deep Learning Approach
Nallasivan G.
Ramachandran V.
Alroobaea R.
Almotiri J.
Computer Systems Science and Engineering, 2023, 45 (02): : 1655 - 1677
[10] Improved Lightweight Deep Learning Algorithm in 3D Reconstruction
Zhang, Tao
Cao, Yi
CMC-COMPUTERS MATERIALS & CONTINUA, 2022, 72 (03): : 5315 - 5325

← 1 2 3 4 5 →