dc.contributor.author | Pinto, Allan | |
dc.contributor.author | Cordova, Manuel | |
dc.contributor.author | Decker, Luis | |
dc.contributor.author | Campana, Jose | |
dc.contributor.author | Souza, Marcos | |
dc.contributor.author | Andreza, Santos | |
dc.contributor.author | Jhonatas, Conceição | |
dc.contributor.author | Gagliardi, Henrique | |
dc.contributor.author | Luvizon, Diogo | |
dc.contributor.author | Torres, Ricardo Da Silva | |
dc.contributor.author | Pedrini, Helio | |
dc.date.accessioned | 2021-03-08T13:07:00Z | |
dc.date.available | 2021-03-08T13:07:00Z | |
dc.date.created | 2020-11-05T21:08:35Z | |
dc.date.issued | 2020 | |
dc.identifier.isbn | 978-1-7281-6395-6 | |
dc.identifier.uri | https://hdl.handle.net/11250/2732196 | |
dc.description.abstract | Stereo vision is a growing topic in computer vision due to the innumerable opportunities and applications this technology offers for the development of modern solutions, such as virtual and augmented reality applications. To enhance the user's experience in three-dimensional virtual environments, the motion parallax estimation is a promising technique to achieve this objective. In this paper, we propose an algorithm for generating parallax motion effects from a single image, taking advantage of state-of-the-art instance segmentation and depth estimation approaches. This work also presents a comparison against such algorithms to investigate the trade-off between efficiency and quality of the parallax motion effects, taking into consideration a multi-task learning network capable of estimating instance segmentation and depth estimation at once. Experimental results and visual quality assessment indicate that the PyD-Net network (depth estimation) combined with Mask R-CNN or FBNet networks (instance segmentation) can produce parallax motion effects with good visual quality. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | IEEE Signal Processing Society | en_US |
dc.relation.ispartof | Proceedings of IEEE international conference on image processing | |
dc.title | Parallax Motion Effect Generation Through Instance Segmentation And Depth Estimation | en_US |
dc.type | Chapter | en_US |
dc.description.version | acceptedVersion | en_US |
dc.source.pagenumber | 1621-1625 | en_US |
dc.identifier.doi | http://dx.doi.org/10.1109/ICIP40778.2020.9191168 | |
dc.identifier.cristin | 1845445 | |
dc.description.localcode | © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | en_US |
cristin.ispublished | true | |
cristin.fulltext | postprint | |
cristin.qualitycode | 1 | |