Saved in:
Bibliographic Details
Main Authors: Han, Dongshen, Lee, Seungkyu, Zhang, Chaoning, Yoon, Heechan, Kwon, Hyukmin, Kim, Hyun-Cheol, Choo, Hyon-Gon
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2307.00212
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916145516249088
author Han, Dongshen
Lee, Seungkyu
Zhang, Chaoning
Yoon, Heechan
Kwon, Hyukmin
Kim, Hyun-Cheol
Choo, Hyon-Gon
author_facet Han, Dongshen
Lee, Seungkyu
Zhang, Chaoning
Yoon, Heechan
Kwon, Hyukmin
Kim, Hyun-Cheol
Choo, Hyon-Gon
contents Glass surfaces of transparent objects and mirrors are not able to be uniquely and explicitly characterized by their visual appearances because they contain the visual appearance of other reflected or transmitted surfaces as well. Detecting glass regions from a single-color image is a challenging task. Recent deep-learning approaches have paid attention to the description of glass surface boundary where the transition of visual appearances between glass and non-glass surfaces are observed. In this work, we analytically investigate how glass surface boundary helps to characterize glass objects. Inspired by prior semantic segmentation approaches with challenging image types such as X-ray or CT scans, we propose separated internal-external boundary attention modules that individually learn and selectively integrate visual characteristics of the inside and outside region of glass surface from a single color image. Our proposed method is evaluated on six public benchmarks comparing with state-of-the-art methods showing promising results.
format Preprint
id arxiv_https___arxiv_org_abs_2307_00212
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Internal-External Boundary Attention Fusion for Glass Surface Segmentation
Han, Dongshen
Lee, Seungkyu
Zhang, Chaoning
Yoon, Heechan
Kwon, Hyukmin
Kim, Hyun-Cheol
Choo, Hyon-Gon
Computer Vision and Pattern Recognition
Glass surfaces of transparent objects and mirrors are not able to be uniquely and explicitly characterized by their visual appearances because they contain the visual appearance of other reflected or transmitted surfaces as well. Detecting glass regions from a single-color image is a challenging task. Recent deep-learning approaches have paid attention to the description of glass surface boundary where the transition of visual appearances between glass and non-glass surfaces are observed. In this work, we analytically investigate how glass surface boundary helps to characterize glass objects. Inspired by prior semantic segmentation approaches with challenging image types such as X-ray or CT scans, we propose separated internal-external boundary attention modules that individually learn and selectively integrate visual characteristics of the inside and outside region of glass surface from a single color image. Our proposed method is evaluated on six public benchmarks comparing with state-of-the-art methods showing promising results.
title Internal-External Boundary Attention Fusion for Glass Surface Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2307.00212