PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models

Author:

Liu Minghua1,Zhu Yinhao2,Cai Hong2,Han Shizhong2,Ling Zhan1,Porikli Fatih2,Su Hao1

Affiliation:

1. UC San Diego

2. Qualcomm AI Research

Publisher

IEEE

Reference81 articles.

1. Compositionally generalizable 3d structure prediction;han;ArXiv Preprint,2020

2. Language grounding with 3d objects;thomason;Conference on Robot Learning,0

3. Label-Efficient Learning on Point Clouds Using Approximate Convex Decompositions

4. KPConv: Flexible and Deformable Convolution for Point Clouds

5. Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation

Cited by 9 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. DAE-Net: Deforming Auto-Encoder for fine-grained shape co-segmentation;Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers '24;2024-07-13

2. Part123: Part-aware 3D Reconstruction from a Single-view Image;Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers '24;2024-07-13

3. Towards Open Vocabulary Learning: A Survey;IEEE Transactions on Pattern Analysis and Machine Intelligence;2024-07

4. FontCLIP: A Semantic Typography Visual‐Language Model for Multilingual Font Applications;Computer Graphics Forum;2024-04-30

5. Inter-Modal Masked Autoencoder for Self-Supervised Learning on Point Clouds;IEEE Transactions on Multimedia;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3