FACNet: Feature alignment fast point cloud completion network  

作　　者：Xinxing Yu Jianyi Li Chi-Chong Wong Chi-Man Vong Yanyan Liang 

机构地区：[1]School of Computer Science and Engineering,Faculty of Innovation Engineering,Macao University of Science and Technology,Taipa,Macao,China [2]Faculty of Science and Technology,University of Macao,Taipa,Macao,China

出　　处：《Computational Visual Media》2025年第1期141-157,共17页计算可视媒体(英文版)

基　　金：supported by the Zhuhai Industry-University-Research Project(No.2220004002411);National Key R&D Program of China(No.2021YFE0205700);Science and Technology Development Fund of Macao(Nos.0070/2020/AMJ,00123/2022/A3,and 0096/2023/RIA2);Zhuhai City Polytechnic Research Project(No.2024KYBS02);Shenzhen Science and Technology Innovation Committee(No.SGDX20220530111001006);the University of Macao under Grants MYRG(Nos.GRG2023-00061-FST UMDF and 2022-00084-FST)。

摘　　要：Point cloud completion aims to infer complete point clouds based on partial 3D point cloud inputs.Various previous methods apply coarseto-fine strategy networks for generating complete point clouds.However,such methods are not only relatively time-consuming but also cannot provide representative complete shape features based on partial inputs.In this paper,a novel feature alignment fast point cloud completion network(FACNet)is proposed to directly and efficiently generate the detailed shapes of objects.FACNet aligns high-dimensional feature distributions of both partial and complete point clouds to maintain global information about the complete shape.During its decoding process,the local features from the partial point cloud are incorporated along with the maintained global information to ensure complete and time-saving generation of the complete point cloud.Experimental results show that FACNet outperforms the state-of-theart on PCN,Completion3D,and MVP datasets,and achieves competitive performance on ShapeNet-55 and KITTI datasets.Moreover,FACNet and a simplified version,FACNet-slight,achieve a significant speedup of 3–10 times over other state-of-the-art methods.

关 键 词：3D point clouds shape completion geometry processing deep learning 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]