SCPNet: Semantic Scene Completion on Point Cloud

doi:10.1109/CVPR52729.2023.01692

	SCPNet: Semantic Scene Completion on Point Cloud
	Xia, Zhaoyang 1; Liu, Youquan 1; Li, Xin 2; Zhu, Xinge 3; Ma, Yuexin4 ; Li, Yikang 1; Hou, Yuenan 1; Qiao, Yu 1
	2023
会议录名称	2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
ISSN	1063-6919
卷号	2023-June
页码	17642-17651
发表状态	已发表
DOI	10.1109/CVPR52729.2023.01692
摘要	Training deep models for semantic scene completion (SSC) is challenging due to the sparse and incomplete input, a large quantity of objects of diverse scales as well as the inherent label noise for moving objects. To address the above-mentioned problems, we propose the following three solutions: 1) Redesigning the completion sub-network. We design a novel completion sub-network, which consists of several Multi-Path Blocks (MPBs) to aggregate multi-scale features and is free from the lossy downsampling operations. 2) Distilling rich knowledge from the multi-frame model. We design a novel knowledge distillation objective, dubbed Dense-to-Sparse Knowledge Distillation (DSKD). It transfers the dense, relation-based semantic knowledge from the multi-frame teacher to the single-frame student, significantly improving the representation learning of the single-frame model. 3) Completion label rectification. We propose a simple yet effective label rectification strategy, which uses off-the-shelf panoptic segmentation labels to remove the traces of dynamic objects in completion labels, greatly improving the performance of deep models especially for those moving objects. Extensive experiments are conducted in two public SSC benchmarks, i.e., SemanticKITTI and SemanticPOSS. Our SCPNet ranks 1st on SemanticKITTI semantic scene completion challenge and surpasses the competitive S3CNet [3] by 7.2 mIoU. SCPNet also outperforms previous completion algorithms on the SemanticPOSS dataset. Besides, our method also achieves competitive results on SemanticKITTI semantic segmentation tasks, showing that knowledge learned in the scene completion is beneficial to the segmentation task.
会议录编者/会议主办者	Amazon Science ; Ant Research ; Cruise ; et al. ; Google ; Lambda
会议名称	IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
出版地	10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA
会议地点	null,Vancouver,CANADA
会议日期	JUN 17-24, 2023
URL	查看原文
收录类别	CPCI-S ; EI
语种	英语
资助项目	National Key R&D Program of China[2022ZD0160100] ; Shanghai Committee of Science and Technology[21DZ1100100]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001062531301091
出版者	IEEE COMPUTER SOC
EI入藏号	20234114867448
原始文献类型	Conference article (CA)
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/346494
专题	信息科学与技术学院_PI研究组_马月昕
通讯作者	Hou, Yuenan
作者单位	1.Shanghai AI Lab, Shanghai, Peoples R China 2.East China Normal Univ, Shanghai, Peoples R China 3.Chinese Univ Hong Kong, Hong Kong, Peoples R China 4.ShanghaiTech Univ, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Xia, Zhaoyang,Liu, Youquan,Li, Xin,et al. SCPNet: Semantic Scene Completion on Point Cloud[C]//Amazon Science, Ant Research, Cruise, et al., Google, Lambda. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA:IEEE COMPUTER SOC,2023:17642-17651.