Human 3D mesh reconstruction from single RGB image based on deep learning network

Wen-Nung Lie; Chun-Yu Lai; Jui-Chiu Chiang; Po-Han Huang

doi:10.1117/12.3058110

5 February 2025 Human 3D mesh reconstruction from single RGB image based on deep learning network

Wen-Nung Lie, Chun-Yu Lai, Jui-Chiu Chiang, Po-Han Huang

Author Affiliations +

Proceedings Volume 13510, International Workshop on Advanced Imaging Technology (IWAIT) 2025; 1351020 (2025) https://doi.org/10.1117/12.3058110
Event: International Workshop on Advanced Imaging Technology (IWAIT) 2025, 2025, Douliu City, Taiwan

Abstract

In recent years, with the rapid development of the artificial intelligence technology, many computer vision applications have been proposed, including Virtual Reality (VR), Augmented Reality (AR), and the metaverse. One of the key technologies to realize these vision applications is "human 3D mesh reconstruction." This paper aims to research the task of reconstructing human 3D mesh model from a single RGB image, with a focus on achieving good reconstruction results while reducing computational costs, thereby establishing advantages for future daily life applications. We propose an improved version of the HyperGraph Convolution Network (HGCN), called the Swift HyperGraph Convolution Network (Swift-HGCN), which allows for faster transmission of information across different parts of the human mesh model. Additionally, we apply the Mamba module to address the high computational complexity caused by the self-attention mechanism in Transformers, while still maintaining good accuracy. Moreover, our system analyzes multi-scale image features and perform multi-stage refinement to reduce reconstruction errors. In the experimental results, our method showed an average vertex position error that is 1.3mm higher than a baseline method, but used only 86.5% of the parameters and had just 17.3% of the computational complexity. This demonstrates that our approach is more suitable for environments with limited computational resources, such as embedded systems.

(2025) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Wen-Nung Lie, Chun-Yu Lai, Jui-Chiu Chiang, and Po-Han Huang "Human 3D mesh reconstruction from single RGB image based on deep learning network", Proc. SPIE 13510, International Workshop on Advanced Imaging Technology (IWAIT) 2025, 1351020 (5 February 2025); https://doi.org/10.1117/12.3058110

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

3D modeling

3D image reconstruction

RGB color model

Data transmission

Convolution

Image restoration

3D image processing

Show All Keywords

Keywords/Phrases

Search In:

Publication Years