MVDC: A Multi-view Dental Completion Model Based on Contrastive Learning

Xunyu YANG; Qingxin DENG; Minghan HUANG; Landu JIANG; Dian ZHANG

doi:10.1109/ICASSP49660.2025.10888840

MVDC: A Multi-view Dental Completion Model Based on Contrastive Learning

Xunyu YANG
, Qingxin DENG
, Minghan HUANG
, Landu JIANG
, Dian ZHANG^*

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

2 Citations (Scopus)

Abstract

Restoring the patient's occlusal function of broken teeth is a challenging task since tooth texture is very complex, a slight deviation may affect the patient's chewing function and temporomandibular joint function. Therefore, how to efficiently repair the complete shape and real surface of the crown is a critical problem. Traditional technologies are hard to restore complete shape of the dental crown or lack inlay surface details, due to dataset limitations and complexity of missing parts. In this paper, we propose a multi-view crown restoration framework MVDC based on contrastive learning. Specifically, MVDC contains: 1) a multi-view generator with a specially designed loss measurement by using contrastive learning; 2) a multi-scale discriminator mechanism able to consider relation and consistency between teeth from different scales; 3) an occlusal groove extraction network to extract the occlusal details. We conducted extensive experiments on existing public datasets. The results showcase the superior performance of MVDC.

Original language	English
Title of host publication	2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 : Proceedings
Editors	Bhaskar D RAO, Isabel TRANCOSO, Gaurav SHARMA, Neelesh B. MEHTA
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	5
ISBN (Electronic)	9798350368741
DOIs	https://doi.org/10.1109/ICASSP49660.2025.10888840
Publication status	Published - 2025
Externally published	Yes
Event	2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 - Hyderabad, India Duration: 6 Apr 2025 → 11 Apr 2025

Publication series

Name	IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings
Publisher	IEEE
ISSN (Print)	1520-6149
ISSN (Electronic)	2379-190X

Conference

Conference	2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025
Abbreviated title	ICASSP 2025
Country/Territory	India
City	Hyderabad
Period	6/04/25 → 11/04/25

Bibliographical note

Publisher Copyright:
© 2025 IEEE.

Funding

The paper is supported by: Stable Support Project of Shenzhen (Project No. 20231122145548001), Shenzhen Grant JCYJ20220531091407016, Futian Healthcare Research Project(No.FTWS069, FTWS055), Shenzhen Hospital (Futian) of Guangzhou University of Chinese Medicine Research Project (No.GZYSY2024010).

Keywords

Contrastive learning
Multi-view
Teeth completion

Access to Document

10.1109/ICASSP49660.2025.10888840

Cite this

YANG, X., DENG, Q., HUANG, M., JIANG, L., & ZHANG, D. (2025). MVDC: A Multi-view Dental Completion Model Based on Contrastive Learning. In B. D. RAO, I. TRANCOSO, G. SHARMA, & N. B. MEHTA (Eds.), 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 : Proceedings (IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP49660.2025.10888840

YANG, Xunyu ; DENG, Qingxin ; HUANG, Minghan et al. / MVDC: A Multi-view Dental Completion Model Based on Contrastive Learning. 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 : Proceedings. editor / Bhaskar D RAO ; Isabel TRANCOSO ; Gaurav SHARMA ; Neelesh B. MEHTA. Institute of Electrical and Electronics Engineers Inc., 2025. (IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings).

@inproceedings{b85ccd78a9d84151962f820778402661,

title = "MVDC: A Multi-view Dental Completion Model Based on Contrastive Learning",

abstract = "Restoring the patient's occlusal function of broken teeth is a challenging task since tooth texture is very complex, a slight deviation may affect the patient's chewing function and temporomandibular joint function. Therefore, how to efficiently repair the complete shape and real surface of the crown is a critical problem. Traditional technologies are hard to restore complete shape of the dental crown or lack inlay surface details, due to dataset limitations and complexity of missing parts. In this paper, we propose a multi-view crown restoration framework MVDC based on contrastive learning. Specifically, MVDC contains: 1) a multi-view generator with a specially designed loss measurement by using contrastive learning; 2) a multi-scale discriminator mechanism able to consider relation and consistency between teeth from different scales; 3) an occlusal groove extraction network to extract the occlusal details. We conducted extensive experiments on existing public datasets. The results showcase the superior performance of MVDC.",

keywords = "Contrastive learning, Multi-view, Teeth completion",

author = "Xunyu YANG and Qingxin DENG and Minghan HUANG and Landu JIANG and Dian ZHANG",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025, ICASSP 2025 ; Conference date: 06-04-2025 Through 11-04-2025",

year = "2025",

doi = "10.1109/ICASSP49660.2025.10888840",

language = "English",

series = "IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "RAO, \{Bhaskar D\} and Isabel TRANCOSO and Gaurav SHARMA and MEHTA, \{Neelesh B.\}",

booktitle = "2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 : Proceedings",

address = "United States",

}

YANG, X, DENG, Q, HUANG, M, JIANG, L & ZHANG, D 2025, MVDC: A Multi-view Dental Completion Model Based on Contrastive Learning. in BD RAO, I TRANCOSO, G SHARMA & NB MEHTA (eds), 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 : Proceedings. IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings, Institute of Electrical and Electronics Engineers Inc., 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025, Hyderabad, India, 6/04/25. https://doi.org/10.1109/ICASSP49660.2025.10888840

MVDC: A Multi-view Dental Completion Model Based on Contrastive Learning. / YANG, Xunyu; DENG, Qingxin; HUANG, Minghan et al.
2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 : Proceedings. ed. / Bhaskar D RAO; Isabel TRANCOSO; Gaurav SHARMA; Neelesh B. MEHTA. Institute of Electrical and Electronics Engineers Inc., 2025. (IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

TY - GEN

T1 - MVDC: A Multi-view Dental Completion Model Based on Contrastive Learning

AU - YANG, Xunyu

AU - DENG, Qingxin

AU - HUANG, Minghan

AU - JIANG, Landu

AU - ZHANG, Dian

PY - 2025

Y1 - 2025

N2 - Restoring the patient's occlusal function of broken teeth is a challenging task since tooth texture is very complex, a slight deviation may affect the patient's chewing function and temporomandibular joint function. Therefore, how to efficiently repair the complete shape and real surface of the crown is a critical problem. Traditional technologies are hard to restore complete shape of the dental crown or lack inlay surface details, due to dataset limitations and complexity of missing parts. In this paper, we propose a multi-view crown restoration framework MVDC based on contrastive learning. Specifically, MVDC contains: 1) a multi-view generator with a specially designed loss measurement by using contrastive learning; 2) a multi-scale discriminator mechanism able to consider relation and consistency between teeth from different scales; 3) an occlusal groove extraction network to extract the occlusal details. We conducted extensive experiments on existing public datasets. The results showcase the superior performance of MVDC.

AB - Restoring the patient's occlusal function of broken teeth is a challenging task since tooth texture is very complex, a slight deviation may affect the patient's chewing function and temporomandibular joint function. Therefore, how to efficiently repair the complete shape and real surface of the crown is a critical problem. Traditional technologies are hard to restore complete shape of the dental crown or lack inlay surface details, due to dataset limitations and complexity of missing parts. In this paper, we propose a multi-view crown restoration framework MVDC based on contrastive learning. Specifically, MVDC contains: 1) a multi-view generator with a specially designed loss measurement by using contrastive learning; 2) a multi-scale discriminator mechanism able to consider relation and consistency between teeth from different scales; 3) an occlusal groove extraction network to extract the occlusal details. We conducted extensive experiments on existing public datasets. The results showcase the superior performance of MVDC.

KW - Contrastive learning

KW - Multi-view

KW - Teeth completion

UR - https://www.scopus.com/pages/publications/105003890510

U2 - 10.1109/ICASSP49660.2025.10888840

DO - 10.1109/ICASSP49660.2025.10888840

M3 - Conference paper (refereed)

AN - SCOPUS:105003890510

T3 - IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings

BT - 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 : Proceedings

A2 - RAO, Bhaskar D

A2 - TRANCOSO, Isabel

A2 - SHARMA, Gaurav

A2 - MEHTA, Neelesh B.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

Y2 - 6 April 2025 through 11 April 2025

ER -

YANG X, DENG Q, HUANG M, JIANG L, ZHANG D. MVDC: A Multi-view Dental Completion Model Based on Contrastive Learning. In RAO BD, TRANCOSO I, SHARMA G, MEHTA NB, editors, 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025 : Proceedings. Institute of Electrical and Electronics Engineers Inc. 2025. (IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings). doi: 10.1109/ICASSP49660.2025.10888840

MVDC: A Multi-view Dental Completion Model Based on Contrastive Learning

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this