3D Shape Segmentation With Potential Consistency Mining and Enhancement

作     者：Shu, Zhenyu Li, Shiyang Xin, Shiqing Liu, Ligang 

作者机构：NingboTech Univ Sch Comp & Data Engn Ningbo 315104 Peoples R China Zhejiang Univ Coll Comp Sci & Technol Hangzhou 310018 Peoples R China Shandong Univ Sch Comp Sci & technol Jinan 250355 Peoples R China Univ Sci & Technol China Sch Math Sci Graph & Geometr Comp Lab Hefei 230026 Anhui Peoples R China 

出 版 物：《IEEE TRANSACTIONS ON MULTIMEDIA》 (IEEE Trans Multimedia)

年 卷 期：2025年第27卷

页      面：133-144页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Foundation of China [62172356, 61872321] Zhejiang Provincial Natural Science Foundation of China [Z25F020010] Ningbo Major Special Projects of the "Science and Technology Innovation [2020Z005, 2021Z012, 2020Z007] 

主　　题：Shape Three-dimensional displays Feature extraction Faces Vectors Point cloud compression Partitioning algorithms Labeling Data mining Accuracy 3D shape segmentation consistency deep learning shape analysis 

摘      要：3D shape segmentation is a crucial task in the field of multimedia analysis and processing, and recent years have seen a surge in research on this topic. However, many existing methods only consider geometric features of 3D shapes and fail to explore the potential connections between faces, limiting their segmentation performance. In this paper, we propose a novel segmentation approach that mines and enhances the potential consistency of 3D shapes to overcome this limitation. The key idea is to mine the consistency between different partitions of 3D shapes and to use the unique consistency enhancement strategy to continuously optimize the consistency features for the network. Our method also includes a comprehensive set of network structures to mine and enhance consistent features, enabling more effective feature extraction and better utilization of contextual information around each face when processing complex shapes. We evaluate our approach on public benchmarks through extensive experiments and demonstrate its effectiveness in achieving higher accuracy than existing methods.