重庆理工大学学报2024，Vol.38Issue(19)：112-121,10.DOI:10.3969/j.issn.1674-8425(z).2024.10.014
融合图卷积残差网络与边收缩池化的VQ-VAE网格重建算法
VQ-VAE mesh reconstruction algorithm integrating graph convolution residual networks and edge contraction pooling
摘要
Abstract
Challenges exist for the effective representation of 3D meshes due to their complexity and irregularity.To address the limitations of conventional graph convolution in propagating and integrating information across 3 D meshes,this paper proposes a 3 D mesh model based on variational autoencoders with vector quantization to explore their latent space for 3D mesh generation.The introduction of residual graph convolution modules,specifically designed for intricate graph structures like triangular meshes,enhances the integration of multi-layered feature information through residual connections,supporting deeper network architectures and significantly improving model performance and generalization.Building upon a reliable edge contraction algorithm for mesh simplification,a hierarchical structure is encoded through robust multi-level pooling and unpooling operations,effectively capturing correspondences between coarser and denser meshes.Meanwhile,in the process of projecting 3D mesh shapes into the latent space,potential feature compression leading to information loss is addressed by employing vector quantization to map latent features to predefined discrete vectors.Our experimental results demonstrate the proposed algorithm learns compact representations for deformable shape collections,delivering outstanding performances in various applications such as shape generation and interpolation.关键词
网格生成/变分量化自编码器/网格插值/图卷积Key words
mesh generation/variational autoencoder/mesh interpolation/graph convolution分类
信息技术与安全科学引用本文复制引用
丁阳,杨华民,韩成,刘宇,卢时禹..融合图卷积残差网络与边收缩池化的VQ-VAE网格重建算法[J].重庆理工大学学报,2024,38(19):112-121,10.基金项目
吉林省自然科学基金项目(20220101134JC) （20220101134JC）
