Show simple item record

dc.contributor.authorDai, Yutongen_US
dc.contributor.authorLu, Haoen_US
dc.contributor.authorShen, Chunhuaen_US
dc.contributor.editorBenes, Bedrich and Hauser, Helwigen_US
dc.date.accessioned2021-02-27T19:02:28Z
dc.date.available2021-02-27T19:02:28Z
dc.date.issued2021
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14179
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14179
dc.description.abstractTraditional portrait matting methods typically consist of a trimap estimation network and a matting network. Here, we propose a new light‐weight portrait matting approach, termed parameter‐sharing portrait matting (PSPM). Different from conventional portrait matting models where the encoder and decoder networks in two tasks are often separately designed, here a single encoder is employed for the two tasks in PSPM, while each task still has its task‐specific decoder. Thus, the role of the encoder is to extract semantic features and two decoders function as a bridge between low‐resolution feature maps generated by the encoder and high‐resolution feature maps for pixel‐wise classification/regression. In particular, three variants capable of implementing the parameter‐sharing portrait matting network are proposed and investigated, respectively. As demonstrated in our experiments, model capacity and computation costs can be reduced significantly, by up to and , respectively, with PSPM, whereas the matting accuracy only slightly deteriorates. In addition, qualitative and quantitative evaluations show that sharing the encoder is an effective way to achieve portrait matting with limited computational budgets, indicating a promising direction for applications of real‐time portrait matting on mobile devices.en_US
dc.publisher© 2021 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltden_US
dc.subjectimage matting
dc.subjectdeep portrait matting
dc.subjectmulti‐task learning
dc.subjectparameter sharing
dc.titleTowards Light‐Weight Portrait Matting via Parameter Sharingen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersArticles
dc.description.volume40
dc.description.number1
dc.identifier.doi10.1111/cgf.14179
dc.identifier.pages151-164


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record