首页|期刊导航|Computational Visual Media|BoostPoint:Boosting point cloud backbones with image pre-training for 3D understanding

BoostPoint:Boosting point cloud backbones with image pre-training for 3D understanding

Honggu Zhou Yakai Zhang Haohan Li Xiaoling Gu Ming Zeng Zizhao Wu

Computational Visual Media2026，Vol.12Issue(1)：P.141-158,18.

Computational Visual Media2026，Vol.12Issue(1)：P.141-158,18.DOI:10.26599/CVM.2025.9450425

BoostPoint:Boosting point cloud backbones with image pre-training for 3D understanding

Honggu Zhou ¹Yakai Zhang ¹Haohan Li ¹Xiaoling Gu ²Ming Zeng ³Zizhao Wu¹

作者信息

1. School of Digital Media Technology,Hangzhou Dianzi University,Hangzhou 310018,China
2. School of Computer Science,Hangzhou Dianzi University,Hangzhou 310018,China
3. School of Informatics,Xiamen University,Xiamen 361005,China
折叠

摘要

关键词

3D point cloud/transfer learning/crossmodal learning/representation learning

分类

信息技术与安全科学

引用本文复制引用

Honggu Zhou,Yakai Zhang,Haohan Li,Xiaoling Gu,Ming Zeng,Zizhao Wu..BoostPoint:Boosting point cloud backbones with image pre-training for 3D understanding[J].Computational Visual Media,2026,12(1):P.141-158,18.

基金项目

supported by the Zhejiang Province Leading Geese Science and Technology Program(No.2025C02155) （No.2025C02155）

the National Natural Science Foundation of China(No.62471168). （No.62471168）

Computational Visual Media

ISSN：2096-0433

访问量0

下载量0

段落导航