Salient Object Detection for Point Clouds

被引:11
作者
Fan, Songlin [1 ,2 ]
Gao, Wei [1 ,2 ]
Li, Ge [1 ]
机构
[1] Peking Univ, Shenzhen Grad Sch, Shenzhen, Peoples R China
[2] Peng Cheng Lab, Shenzhen, Peoples R China
来源
COMPUTER VISION - ECCV 2022, PT XXVIII | 2022年 / 13688卷
基金
国家重点研发计划;
关键词
Salient object detection; Point cloud; Dataset; Baseline; SEGMENTATION; DENSE;
D O I
10.1007/978-3-031-19815-1_1
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper researches the unexplored task-point cloud salient object detection (SOD). Differing from SOD for images, we find the attention shift of point clouds may provoke saliency conflict, i.e., an object paradoxically belongs to salient and non-salient categories. To eschew this issue, we present a novel view-dependent perspective of salient objects, reasonably reflecting the most eye-catching objects in point cloud scenarios. Following this formulation, we introduce PCSOD, the first dataset proposed for point cloud SOD consisting of 2,872 in-/out-door 3D views. The samples in our dataset are labeled with hierarchical annotations, e.g., super-/sub-class, bounding box, and segmentation map, which endows the brilliant generalizability and broad applicability of our dataset verifying various conjectures. To evidence the feasibility of our solution, we further contribute a baseline model and benchmark five representative models for a comprehensive comparison. The proposed model can effectively analyze irregular and unordered points for detecting salient objects. Thanks to incorporating the task-tailored designs, our method shows visible superiority over other baselines, producing more satisfactory results. Extensive experiments and discussions reveal the promising potential of this research field, paving the way for further study.
引用
收藏
页码:1 / 19
页数:19
相关论文
共 63 条
[11]  
Fu KR, 2021, Arxiv, DOI arXiv:2010.04968
[12]   Unified Information Fusion Network for Multi-Modal RGB-D and RGB-T Salient Object Detection [J].
Gao, Wei ;
Liao, Guibiao ;
Ma, Siwei ;
Li, Ge ;
Liang, Yongsheng ;
Lin, Weisi .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (04) :2091-2106
[13]   Point-wise saliency detection on 3D point clouds via covariance descriptors [J].
Guo, Yu ;
Wang, Fei ;
Xin, Jingmin .
VISUAL COMPUTER, 2018, 34 (10) :1325-1338
[14]  
Hackel T, 2017, Arxiv, DOI [arXiv:1704.03847, DOI 10.5194/ISPRS-ANNALS-IV-1-W1-91-2017]
[15]   Deeply Supervised Salient Object Detection with Short Connections [J].
Hou, Qibin ;
Cheng, Ming-Ming ;
Hu, Xiaowei ;
Borji, Ali ;
Tu, Zhuowen ;
Torr, Philip H. S. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2019, 41 (04) :815-828
[16]   Learning Semantic Segmentation of Large-Scale Point Clouds With Random Sampling [J].
Hu, Qingyong ;
Yang, Bo ;
Xie, Linhai ;
Rosa, Stefano ;
Guo, Yulan ;
Wang, Zhihua ;
Trigoni, Niki ;
Markham, Andrew .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (11) :8338-8354
[17]   A model of saliency-based visual attention for rapid scene analysis [J].
Itti, L ;
Koch, C ;
Niebur, E .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1998, 20 (11) :1254-1259
[18]  
Kim G, 2008, IEEE WORK APP COMP, P145
[19]   Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models [J].
Klokov, Roman ;
Lempitsky, Victor .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :863-872
[20]   Depth Matters: Influence of Depth Cues on Visual Saliency [J].
Lang, Congyan ;
Nguyen, Tam V. ;
Katti, Harish ;
Yadati, Karthik ;
Kankanhalli, Mohan ;
Yan, Shuicheng .
COMPUTER VISION - ECCV 2012, PT II, 2012, 7573 :101-115