Đồ án tốt nghiệp - Development of a comprehensive deep learning-based system for 3D RF 2 I

Tên môn học: Khóa luận tốt nghiệp

Giá: 53.000đ

Tổng thanh toán:

53.000đ

Người đăng tải:

#10377

Chi tiết tài liệu :

Đồ án tốt nghiệp ngành Công nghệ Kỹ thuật máy tính - Development of a comprehensive deep learning-based system for 3D reconstruction from 2D images - Trường Đại học Sư phạm Kỹ thuật Thành phố Hồ Chí Minh (HCMUTE)

Định dạng	PDF
Dung lượng	7.12 MB
Số trang	76
Ngành	CNKT máy tính

Lượt xem	44
Ngày đăng	17/01/2026

HCMC UNIVERSITY OF TECHNOLOGY AND EDUCATION
FACULTY OF INTERNATIONAL EDUCATION

Development of a Comprehensive Deep Learning-Based
System for 3D Reconstruction from 2D Images
COMPUTER ENGINEERING TECHNOLOGY

Student name: TRẦN MINH KHÔI
Student ID:

20119135

Student name: NGUYỄN TIẾN ĐẠT
Student ID:

20119125

Supervisor:

HUỲNH THẾ THIỆN

Ho Chi Minh City - 01/2025

HCMC UNIVERSITY OF TECHNOLOGY AND EDUCATION
FACULTY OF INTERNATIONAL EDUCATION

Development of a Comprehensive Deep Learning-Based
System for 3D Reconstruction from 2D Images
COMPUTER ENGINEERING TECHNOLOGY

Student name: TRẦN MINH KHÔI
Student ID:

20119135

Student name: NGUYỄN TIẾN ĐẠT
Student ID:

20119125

Supervisor:

HUỲNH THẾ THIỆN

Ho Chi Minh City - 01/2025

THE SOCIALIST REPUBLIC OF VIETNAM

Independence – Freedom– Happiness

Ho Chi Minh City, December 28, 2024

GRADUATION PROJECT ASSIGNMENT
Student name: ___Tran Minh Khoi________

Student ID: _____20119135____

Student name: ___Nguyen Tien Dat_______

Student ID: _____20119125______

Major: __Computer Engineering Technology_ Class: ______20119CLA__________
Supervisor: __ Huynh The Thien, PhD_______ Phone number: _________________
Date of assignment: _____________________ Date of submission: _____________
1. Project title: ___Development of a Comprehensive Deep Learning-Based System for 3D
Reconstruction from 2D Images______
2. Initial materials provided by supervisor: Idea and scientific papers as references
3. Content of the project: The thesis develops a deep learning-based system for 3D reconstruction from
2D images, integrating state-of-the-art models like Zero123 Plus and InstantMesh for high-quality
reconstructions with a user-friendly web interface.

4. Final product: A ready-to-run and accessible 3D reconstruction platform optimized for applications in
gaming, cultural heritage, and medical imaging.
CHAIR OF THE PROGRAM
(Sign with full name)

SUPERVISOR

(Sign with full name)

THE SOCIALIST REPUBLIC OF VIETNAM

Independence – Freedom– Happiness

SUPERVISOR’S EVALUATION SHEET
Student name: .................Tran Minh Khoi....................... Student ID: ........20119135.........
Student name: .................Nguyen Tien Dat......................Student ID: .........20119125........
Major: ........................Computer Engineering Technology......................................................
Project title: Development of a Comprehensive Deep Learning-Based System fo
...

...
,”
in 2021 International Conference on Networking Systems of AI (INSAI), 2021, pp.
129–135.
[4] J. Xu, W. Cheng, Y. Gao, X. Wang, S. Gao, and Y. Shan, “Instantmesh: Efficient
3d mesh generation from a single image with sparse-view large reconstruction
models,” 2024. [Online]. Available: https://arxiv.org/abs/2404.07191
[5] M. Chen, S. Mei, J. Fan, and M. Wang, “An overview of diffusion models:
Applications, guided generation, statistical rates and optimization,” 2024. [Online].
Available: https://arxiv.org/abs/2404.07771
[6] A. Moncef and A. K. M’hamed, “A review on 3d reconstruction techniques from
2d images,” 02 2020, pp. 510–522.
[7] A. Horé and D. Ziou, “Image quality metrics: Psnr vs. ssim,” in 2010 20th International Conference on Pattern Recognition, 2010, pp. 2366–2369.
[8] R. Zhang, P. Isola, A. A. Efros, E. Shechtman, and O. Wang, “The unreasonable
effectiveness of deep features as a perceptual metric,” 2018. [Online]. Available:
https://arxiv.org/abs/1801.03924
[9] R. Chauhan, K. K. Ghanshala, and R. Joshi, “Convolutional neural network (cnn)
for image detection and recognition,” in 2018 First International Conference on
Secure Cyber Computing and Communication (ICSCCC), 2018, pp. 278–282.
[10] K. Han, Y. Wang, H. Chen, X. Chen, J. Guo, Z. Liu, Y. Tang, A. Xiao, C. Xu,
Y. Xu, Z. Yang, Y. Zhang, and D. Tao, “A survey on vision transformer,” IEEE
Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 1, pp. 87–
110, 2023.
[11] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner,
M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby,
61

“An image is worth 16x16 words: Transformers for image recognition at scale,”
2021. [Online]. Available: https://arxiv.org/abs/2010.11929
[12] R. Shi, H. Chen, Z. Zhang, M. Liu, C. Xu, X. Wei, L. Chen, C. Zeng, and H. Su,
“Zero123++: a single image to consistent multi-view diffusion base model,” 2023.
[13] L. Downs, A. Francis, N. Koenig, B. Kinman, R. Hickman, K. Reymann, T. B.
McHugh, and V. Vanhoucke, “Google scanned objects: A high-quality dataset of
3d scanned household items,” in 2022 International Conference on Robotics and
Automation (ICRA), 2022, pp. 2553–2560.
[14] G. Brazil, A. Kumar, J. Straub, N. Ravi, J. Johnson, and G. Gkioxari, “Omni3d: A
large and model for 3d object detection in the wild,” in 2023 IEEE/CVF
Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp.
13 154–13 164.

62