首页|View-aligned pixel-level feature aggregation for 3D shape classification

View-aligned pixel-level feature aggregation for 3D shape classification

扫码查看
原文链接
  • NETL
  • NSTL
  • Elsevier
Multi-view 3D shape classification， which identifies a 3D shape based on its 2D views rendered from different viewpoints， has emerged as a promising method of shape understanding。 A key building block in these methods is cross-view feature aggregation。 However， existing methods dominantly follow the "extract-then-aggregate" pipeline for view-level global feature aggregation， leaving cross-view pixel-level feature interaction under-explored。 To tackle this issue， we develop a "fuse-while-extract" pipeline， with a novel View-aligned Pixel-level Fusion (VPF) module to fuse cross-view pixel-level features originating from the same 3D part。 We first reconstruct the 3D coordinate of each feature via the rasterization results， then match and fuse the features via spatial neighbor searching。 Incorporating the proposed VPF module with ResNetl8 backbone， we build a novel view-aligned multi-view network， which conducts feature extraction and cross-view fusion alternatively。 Extensive experiments have demonstrated the effectiveness of the VPF module as well as the excellent performance of the proposed network。

Multi-view recognition3D model classificationPixel-wise fusion

Yong Xu、Shaohui Pan、Ruotao Xu、Haibin Ling

展开 >

South China University of Technology, School of Computer Science and Engineering, Guangzhou, 510000, China||PaZhou Laboratory of Guangzhou, Guangzhou, 518000, China||Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis, Guangzhou, 510000, China

South China University of Technology, School of Computer Science and Engineering, Guangzhou, 510000, China

Institute of Super Robotics, South China University of Technology, Guangzhou, 510000, China

Department of Computer Science, Stony Brook University, Stony Brook, 11794, USA

展开 >

2024

10.1016/j.cviu.2024.104098

Computer vision and image understanding

Computer vision and image understanding

EISCI
ISSN：1077-3142
年,卷(期)：2024.248(Nov.)
  • 74