| Full text | |
| Author(s): Show less - |
Pinto, Allan
;
Cordova, Manuel A.
;
Decker, Luis G. L.
;
Flores-Campana, Jose L.
;
Souza, Marcos R.
;
dos Santos, Andreza A.
;
Conceicao, Jhonatas S.
;
Gagliardi, Henrique F.
;
Luvizon, Diogo C.
;
Torres, Ricardo da S.
;
Pedrini, Helio
;
IEEE
Total Authors: 12
|
| Document type: | Journal article |
| Source: | 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP); v. N/A, p. 5-pg., 2020-01-01. |
| 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. (AU) | |
| FAPESP's process: | 19/16253-1 - Unraveling the secret of Brazilian and Dutch soccer by capturing successful elements of playing style and playing strategies |
| Grantee: | Allan da Silva Pinto |
| Support Opportunities: | Scholarships in Brazil - Post-Doctoral |
| FAPESP's process: | 16/50250-1 - The secret of playing football: Brazil versus the Netherlands |
| Grantee: | Sergio Augusto Cunha |
| Support Opportunities: | Research Projects - Thematic Grants |
| FAPESP's process: | 17/12646-3 - Déjà vu: feature-space-time coherence from heterogeneous data for media integrity analytics and interpretation of events |
| Grantee: | Anderson de Rezende Rocha |
| Support Opportunities: | Research Projects - Thematic Grants |