Enhanced Boundary Learning for Glass-like Object Segmentation
Hao, He1,2; Xiangtai, Li3; Guangliang, Cheng4,6; Jianping, Shi4; Yunhai, Tong3; Gaofeng, Meng1,2,5; Véronique Prinet1; LuBin, Weng1
2021-10
Conference NameProceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)
Pages15859-15868
Conference Date2021-10-11 -> 2021-10-17
Conference Place线上会议
Abstract

Glass-like objects such as windows, bottles, and mirrors exist widely in the real world. Sensing these objects has many applications, including robot navigation and grasping.
However, this task is very challenging due to the arbitrary scenes behind glass-like objects. This paper aims to solve the glass-like object segmentation problem via enhanced boundary learning. In particular, we first propose a novel refined differential module that outputs finer boundary cues. We then introduce an edge-aware point-based graph convolution network module to model the global shape along the boundary. We use these two modules to design a decoder that generates accurate and clean segmentation results, especially on the object contours. Both modules are lightweight and effective: they can be embedded into various segmentation models. In extensive experiments on three recent glass-like object segmentation datasets, including Trans10k, MSD, and GDD, our approach establishes new state-of-the-art results. We also illustrate the strong generalization properties of our method on three generic segmentation datasets, including Cityscapes, BDD, and COCO Stuff. Code and models will available for further research.

KeywordSemantic Segmentation Glass-like Object Segmentation Boundary Processing
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/48651
Collection多模态人工智能系统全国重点实验室_先进时空数据分析与学习
Corresponding AuthorLuBin, Weng
Affiliation1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
3.Key Laboratory of Machine Perception (MOE), Peking University
4.SenseTime Group Research
5.Centre for Artificial Intelligence and Robotics, HK Institute of Science & Innovation, CAS
6.Shanghai AI Lab
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Hao, He,Xiangtai, Li,Guangliang, Cheng,et al. Enhanced Boundary Learning for Glass-like Object Segmentation[C],2021:15859-15868.
Files in This Item: Download All
File Name/Size DocType Version Access License
He_Enhanced_Boundary(7575KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Hao, He]'s Articles
[Xiangtai, Li]'s Articles
[Guangliang, Cheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Hao, He]'s Articles
[Xiangtai, Li]'s Articles
[Guangliang, Cheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Hao, He]'s Articles
[Xiangtai, Li]'s Articles
[Guangliang, Cheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: He_Enhanced_Boundary_Learning_for_Glass-Like_Object_Segmentation_ICCV_2021_paper.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.