Matches in SemOpenAlex for { <https://semopenalex.org/work/W2294841639> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W2294841639 abstract "Optics with long focal length have been extensively used for shooting 2D cinema and television, either to virtually get closer to the scene or to produce an aesthetical effect through the deformation of the perspective. However, in 3D cinema or television, the use of long focal length either creates a “cardboard effect” or causes visual divergence. To overcome this problem, state-of-the-art methods use disparity mapping techniques, which is a generalization of view interpolation, and generate new stereoscopic pairs from the two image sequences. We propose to use more than two cameras to solve for the remaining issues in disparity mapping methods.In the first part of the thesis, we review the causes of visual fatigue and visual discomfort when viewing a stereoscopic film. We then model the depth perception from stereopsis of a 3D scene shot with two cameras, and projected in a movie theater or on a 3DTV. We mathematically characterize this 3D distortion, and derive the mathematical constraints associated with the causes of visual fatigue and discomfort. We illustrate these 3D distortions with a new interactive software, “The Virtual Projection Room”.In order to generate the desired stereoscopic images, we propose to use image-based rendering. Those techniques usually proceed in two stages. First, the input images are warped into the target view, and then the warped images are blended together. The warps are usually computed with the help of a geometric proxy (either implicit or explicit). Image blending has been extensively addressed in the literature and a few heuristics have proven to achieve very good performance. Yet the combination of the heuristics is not straightforward, and requires manual adjustment of many parameters.In this thesis, we propose a new Bayesian approach to the problem of novel view synthesis, based on a generative model taking into account the uncertainty of the image warps in the image formation model. The Bayesian formalism allows us to deduce the energy of the generative model and to compute the desired images as the Maximum a Posteriori estimate. The method outperforms state-of-the-art image-based rendering techniques on challenging datasets. Moreover, the energy equations provide a formalization of the heuristics widely used in image-based rendering techniques. Besides, the proposed generative model also addresses the problem of super-resolution, allowing to render images at a higher resolution than the initial ones.In the last part of this thesis, we apply the new rendering technique to the case of the stereoscopic zoom and show its performance." @default.
- W2294841639 created "2016-06-24" @default.
- W2294841639 creator A5009679088 @default.
- W2294841639 date "2015-10-14" @default.
- W2294841639 modified "2023-09-24" @default.
- W2294841639 title "Camera Models and algorithms for 3D video content creation" @default.
- W2294841639 hasPublicationYear "2015" @default.
- W2294841639 type Work @default.
- W2294841639 sameAs 2294841639 @default.
- W2294841639 citedByCount "0" @default.
- W2294841639 crossrefType "dissertation" @default.
- W2294841639 hasAuthorship W2294841639A5009679088 @default.
- W2294841639 hasConcept C121684516 @default.
- W2294841639 hasConcept C126057942 @default.
- W2294841639 hasConcept C12713177 @default.
- W2294841639 hasConcept C154945302 @default.
- W2294841639 hasConcept C205711294 @default.
- W2294841639 hasConcept C31972630 @default.
- W2294841639 hasConcept C41008148 @default.
- W2294841639 hasConceptScore W2294841639C121684516 @default.
- W2294841639 hasConceptScore W2294841639C126057942 @default.
- W2294841639 hasConceptScore W2294841639C12713177 @default.
- W2294841639 hasConceptScore W2294841639C154945302 @default.
- W2294841639 hasConceptScore W2294841639C205711294 @default.
- W2294841639 hasConceptScore W2294841639C31972630 @default.
- W2294841639 hasConceptScore W2294841639C41008148 @default.
- W2294841639 hasLocation W22948416391 @default.
- W2294841639 hasOpenAccess W2294841639 @default.
- W2294841639 hasPrimaryLocation W22948416391 @default.
- W2294841639 hasRelatedWork W1515902347 @default.
- W2294841639 hasRelatedWork W1950334791 @default.
- W2294841639 hasRelatedWork W2103997188 @default.
- W2294841639 hasRelatedWork W2140950877 @default.
- W2294841639 hasRelatedWork W2185098726 @default.
- W2294841639 hasRelatedWork W2268795322 @default.
- W2294841639 hasRelatedWork W2334173380 @default.
- W2294841639 hasRelatedWork W2401689132 @default.
- W2294841639 hasRelatedWork W2402296773 @default.
- W2294841639 hasRelatedWork W2737663484 @default.
- W2294841639 hasRelatedWork W2790433428 @default.
- W2294841639 hasRelatedWork W2902492297 @default.
- W2294841639 hasRelatedWork W2982966540 @default.
- W2294841639 hasRelatedWork W3109585842 @default.
- W2294841639 hasRelatedWork W3131986035 @default.
- W2294841639 hasRelatedWork W3158548918 @default.
- W2294841639 hasRelatedWork W3180232145 @default.
- W2294841639 hasRelatedWork W3205778533 @default.
- W2294841639 hasRelatedWork W3214564114 @default.
- W2294841639 hasRelatedWork W78564536 @default.
- W2294841639 isParatext "false" @default.
- W2294841639 isRetracted "false" @default.
- W2294841639 magId "2294841639" @default.
- W2294841639 workType "dissertation" @default.