GlassNet: Label Decoupling‐based Three‐stream Neural Network for Robust Image Glass Detection

Simple item page
dc.contributor.authorZheng, Chengyuen_US
dc.contributor.authorShi, Dingen_US
dc.contributor.authorYan, Xuefengen_US
dc.contributor.authorLiang, Dongen_US
dc.contributor.authorWei, Mingqiangen_US
dc.contributor.authorYang, Xinen_US
dc.contributor.authorGuo, Yanwenen_US
dc.contributor.authorXie, Haoranen_US
dc.contributor.editorHauser, Helwig and Alliez, Pierreen_US
dc.date.accessioned2022-03-25T12:31:06Z
dc.date.available2022-03-25T12:31:06Z
dc.date.issued2022
dc.description.abstractMost of the existing object detection methods generate poor glass detection results, due to the fact that the transparent glass shares the same appearance with arbitrary objects behind it in an image. Different from traditional deep learning‐based wisdoms that simply use the object boundary as an auxiliary supervision, we exploit label decoupling to decompose the original labelled ground‐truth (GT) map into an interior‐diffusion map and a boundary‐diffusion map. The GT map in collaboration with the two newly generated maps breaks the imbalanced distribution of the object boundary, leading to improved glass detection quality. We have three key contributions to solve the transparent glass detection problem: (1) We propose a three‐stream neural network (call GlassNet for short) to fully absorb beneficial features in the three maps. (2) We design a multi‐scale interactive dilation module to explore a wider range of contextual information. (3) We develop an attention‐based boundary‐aware feature Mosaic module to integrate multi‐modal information. Extensive experiments on the benchmark dataset exhibit clear improvements of our method over SOTAs, in terms of both the overall glass detection accuracy and boundary clearness.en_US
dc.description.number1
dc.description.sectionheadersMajor Revision from Pacific Graphics
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14441
dc.identifier.issn1467-8659
dc.identifier.pages377-388
dc.identifier.urihttps://doi.org/10.1111/cgf.14441
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14441
dc.publisher© 2022 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltden_US
dc.subjectimage processing
dc.subjectimage and video processing
dc.subjectimage segmentation
dc.subjectimage and video processing
dc.subjectcomputer vision–shape recognition
dc.subjectmethods and applications
dc.titleGlassNet: Label Decoupling‐based Three‐stream Neural Network for Robust Image Glass Detectionen_US
Files
Collections
41-Issue 1