Show simple item record

dc.contributor.authorZhang, Yujiaen_US
dc.contributor.authorPerusquia-Hernández, Monicaen_US
dc.contributor.authorIsoyama, Naoyaen_US
dc.contributor.authorKawai, Norihikoen_US
dc.contributor.authorUchiyama, Hideakien_US
dc.contributor.authorSakata, Nobuchikaen_US
dc.contributor.authorKiyokawa, Kiyoshien_US
dc.contributor.editorTheophilus Teoen_US
dc.contributor.editorRyota Kondoen_US
dc.date.accessioned2022-11-29T07:23:36Z
dc.date.available2022-11-29T07:23:36Z
dc.date.issued2022
dc.identifier.isbn978-3-03868-192-2
dc.identifier.issn1727-530X
dc.identifier.urihttps://doi.org/10.2312/egve.20221293
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/egve20221293
dc.description.abstractWe propose a method to relight scenes in a single image while removing unwanted objects by the combination of 3D-aware inpainting and relighting for a new functionality in image editing. First, the proposed method estimates the depth image from an RGB image using single-view depth estimation. Next, the RGB and depth images are masked by the user by specifying unwanted objects. Then, the masked RGB and depth images are simultaneously inpainted by our proposed neural network. For relighiting, a 3D mesh model is first reconstructed from the inpainted depth image, and is then relit with a standard relighting pipeline. In this process, removing cast shadows and sky areas and albedo estimation are optionally performed to suppress the artifacts in outdoor scenes. Through these processes, various types of relighting can be achieved from a single photograph while excluding the colors and shapes of unwanted objects.en_US
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies -> Image processing; Human-centered computing -> Mixed / augmented reality
dc.subjectComputing methodologies
dc.subjectImage processing
dc.subjectHuman centered computing
dc.subjectMixed / augmented reality
dc.title3D-Aware Image Relighting with Object Removal from Single Imageen_US
dc.description.seriesinformationICAT-EGVE 2022 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments - Posters and Demos
dc.description.sectionheadersPosters
dc.identifier.doi10.2312/egve.20221293
dc.identifier.pages13-14
dc.identifier.pages2 pages


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International License
Except where otherwise noted, this item's license is described as Attribution 4.0 International License