Full Text:   <109>

CLC number: 

On-line Access: 2024-11-05

Received: 2024-04-29

Revision Accepted: 2024-09-18

Crosschecked: 0000-00-00

Cited: 0

Clicked: 201

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
Open peer comments

Journal of Zhejiang University SCIENCE C 1998 Vol.-1 No.-1 P.

http://doi.org/10.1631/FITEE.2400344


Zhiwei ZHU, Xiang GAO, Lu YU, Yiyi LIAO


Author(s):  College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China

Affiliation(s):  Zhejiang Provincial Key Laboratory of Information Processing, Communication and Networking (IPCAN), Hangzhou 310027, China

Corresponding email(s):   zhuzhiwei21@zju.edu.cn, xiangg@zju.edu.cn, yul@zju.edu.cn, yiyi.liao@zju.edu.cn

Key Words:  Geometry processing, Mesh refinement, Mesh subdivision, Neural network, Disentangled representation learning, Graph attention


College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China. Zhiwei ZHU, Xiang GAO, Lu YU, Yiyi LIAO[J]. Frontiers of Information Technology & Electronic Engineering, 1998, -1(-1): .

@article{title="Zhiwei ZHU, Xiang GAO, Lu YU, Yiyi LIAO",
author="College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="-1",
number="-1",
pages="",
year="1998",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2400344"
}

%0 Journal Article
%T Zhiwei ZHU, Xiang GAO, Lu YU, Yiyi LIAO
%A College of Information Science and Electronic Engineering
%A Zhejiang University
%A Hangzhou 310027
%A China
%J Journal of Zhejiang University SCIENCE C
%V -1
%N -1
%P
%@ 2095-9184
%D 1998
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2400344

TY - JOUR
T1 - Zhiwei ZHU, Xiang GAO, Lu YU, Yiyi LIAO
A1 - College of Information Science and Electronic Engineering
A1 - Zhejiang University
A1 - Hangzhou 310027
A1 - China
J0 - Journal of Zhejiang University Science C
VL - -1
IS - -1
SP -
EP -
%@ 2095-9184
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2400344


Abstract: 
Subdivision is a widely used technique for mesh refinement. Classic methods rely on fixed manuallydefined weighting rules and struggle to generate a finer mesh with appropriate details, while advanced neural subdivision methods achieve data-driven nonlinear subdivision but lack robustness, suffering from limited subdivision levels and artifacts on novel shapes. To address these issues, this paper introduces a neural mesh refinement (NMR) method that uess a learned geometric prior on fine shapes to adaptively refine coarse meshes through subdivision, demonstrating robust generalization. Our key insight is that it is necessary to disentangle the network from nonstructural information such as scale, rotation, and translation, enabling it to focus on learning and applying the structural priors of local patches for adaptive refinement. For this purpose, we introduce an intrinsic structure descriptor and a locally adaptive neural filter. The intrinsic structure descriptor excludes the non-structural information to align local patches, thereby stabilizing the input feature space and enabling the network to robustly extract structural priors. The proposed neural filter, using a graph attention mechanism, extracts local structural features and adapts learned priors to local patches. Additionally, we observe that Charbonnier loss can alleviate over-smoothing compared to L2 loss. By combining these design choices, our method gains robust geometric learning and locally adaptive capabilities, enhancing generalization to unseen shapes and arbitrary refinement levels. We evaluate our method on a diverse set of complex three-dimensional (3D) shapes and show that it outperforms existing subdivision methods in terms of geometry quality.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2024 Journal of Zhejiang University-SCIENCE