Cascaded Segmented Matting Network for Human Matting

Simple item page
dc.citation.volume9
dc.contributor.authorLiu B
dc.contributor.authorJing H
dc.contributor.authorQu G
dc.contributor.authorGuesgen HW
dc.contributor.editorRaval MS
dc.date.accessioned2023-11-13T22:18:36Z
dc.date.accessioned2023-11-20T01:37:36Z
dc.date.available2021-11-04
dc.date.available2023-11-13T22:18:36Z
dc.date.available2023-11-20T01:37:36Z
dc.date.issued2021-11-04
dc.description.abstractHuman matting, high quality extraction of humans from natural images, is crucial for a wide variety of applications such as virtual reality, augmented reality, entertainment and so on. Since the matting problem is an ill-posed problem, most previous methods rely on extra user inputs such as trimap or scribbles as guidance to estimate alpha value for the pixels that are in the unknown region of the trimap. This phenomenon makes it difficult to be applied to large scale data. In order to solve these problems, we studied the unique role of semantics and details in image matting, and decomposed the matting task into two sub-tasks: trimap segmentation based on high-level semantic information and alpha regression based on low-level detailed information. Specifically, we proposed a novel Cascaded Segmented Matting Network (CSMNet), which uses a shared encoder and two separate decoders to learn these two tasks in a collaborative way to achieve the end-to-end human image matting. In addition, we established a large-scale dataset with 14,000 fine-labeled human matting images. A background dataset is also built to simulate real pictures. Comprehensive empirical studies on above datasets demonstrate that CSMNet could produce a stable and accurate alpha matte without the input of trimap and achieve an evaluation value that is comparable to the algorithm that requires trimap.
dc.description.confidentialfalse
dc.format.pagination157182-157191
dc.identifier.author-urlhttp://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000724460200001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=c5bb3b2499afac691c2e3c1a83ef6fef
dc.identifier.citationLiu B, Jing H, Qu G, Guesgen HW. (2021). Cascaded Segmented Matting Network for Human Matting. IEEE Access. 9. (pp. 157182-157191).
dc.identifier.doi10.1109/ACCESS.2021.3125356
dc.identifier.eissn2169-3536
dc.identifier.elements-typejournal-article
dc.identifier.issn2169-3536
dc.identifier.urihttps://mro.massey.ac.nz/handle/10179/69112
dc.languageEnglish
dc.publisherIEEE
dc.publisher.urihttps://ieeexplore.ieee.org/document/9600805
dc.relation.isPartOfIEEE Access
dc.rightsCC BY-NC-ND 4.0
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectImage segmentation
dc.subjectSemantics
dc.subjectTask analysis
dc.subjectSaliency detection
dc.subjectFeature extraction
dc.subjectDecoding
dc.subjectLicenses
dc.subjectHuman matting
dc.subjectsemantic segmentation
dc.subjectsalient object detection
dc.titleCascaded Segmented Matting Network for Human Matting
dc.typeJournal article
pubs.elements-id449599
pubs.organisational-groupOther
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
449599 PDF.pdf
Size:
1.06 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Journal Articles