Du, Liang, Tan, Jingang, Xue, Xiangyang, Chen, Lili, Wen, Hongkai, Feng, Jianfeng, Li, Jiamao and Zhang, Xiaolin (2020) 3DCFS : Fast and robust joint 3D semantic-instance segmentation via coupled feature selection. In: IEEE International Conference on Robotics and Automaion, Paris, France, 31 May - 4 Jun 2020 (In Press)

Preview

PDF WRAP-3DCFS-Fast-joint-3D-semantic-segmentation-Wen-2020.pdf - Accepted Version - Requires a PDF viewer. Download (5Mb) | Preview

Request Changes to record.

Abstract

We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation. Inspired by the human scene perception process, we design a novel coupled feature selection module, named CFSM, that adaptively selects and fuses the reciprocal semantic and instance features from two tasks in a coupled manner. To further boost the performance of the instance segmentation task in our 3DCFS, we investigate a loss function that helps the model learn to balance the magnitudes of the output embedding dimensions during training, which makes calculating the Euclidean distance more reliable and enhances the generalizability of the model. Extensive experiments demonstrate that our 3DCFS outperforms state-of-the-art methods on benchmark datasets in terms of accuracy, speed and computational cost.

Item Type:	Conference Item (Paper)
Subjects:	Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software T Technology > TA Engineering (General). Civil engineering (General) T Technology > TS Manufactures
Divisions:	Faculty of Science > Computer Science
Library of Congress Subject Headings (LCSH):	Three-dimensional printing , Image segmentation , Image processing -- Digital techniques , Computer vision
Publisher:	IEEE
Official Date:	2020
Dates:	Date Event 2020 Published 31 January 2020 Accepted
Date of first compliant deposit:	17 April 2020
Status:	Peer Reviewed
Publication Status:	In Press
Publisher Statement:	© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Access rights to Published version:	Restricted or Subscription Access
RIOXX Funder/Project Grant:	Project/Grant ID RIOXX Funder Name Funder ID B18015 Higher Education Discipline Innovation Project http://dx.doi.org/10.13039/501100013314 91630314 [NSFC] National Natural Science Foundation of China http://dx.doi.org/10.13039/501100001809 16JC1420402 Shanghai Association for Science and Technology http://dx.doi.org/10.13039/100010098 2018SHZDZX01 Science and Technology Commission of Shanghai Municipality http://dx.doi.org/10.13039/501100003399 UNSPECIFIED UNSPECIFIED
Conference Paper Type:	Paper
Title of Event:	IEEE International Conference on Robotics and Automaion
Type of Event:	Conference
Location of Event:	Paris, France
Date(s) of Event:	31 May - 4 Jun 2020

Request changes or add full text files to a record

Repository staff actions (login required)

View Item

Downloads