 |
|
|
|
| HAL: hal-00628013, version 1 |
| Detailed view |  Export this paper |
|
|
| IEEE International Conference on Image Processing (ICIP), Brussels : Belgique (2011) |
|
|
|
|
| Object-based Layered Depth Images for improved virtual view synthesis in rate-constrained context |
|
|
| Vincent Jantet 1Christine Guillemot 2 |
|
|
| (2011) |
|
|
|
| Layered Depth Image (LDI) representations are attractive compact representations for multi-view videos. Any virtual viewpoint can be rendered from LDI by using view synthesis technique. However, rendering from classical LDI leads to annoying visual artifacts, such as cracks and disocclusions. Visual quality gets even worse after a DCT-based compression of the LDI, because of blurring effects on depth discontinuities. In this paper, we propose a novel object-based LDI representation, improving synthesized virtual views quality, in a rate-constrained context. Pixels from each LDI layer are reorganised to enhance depth continuity. |
|
|
|
|
|
|
|
|
|
|
|
| 1: | École normale supérieure de Cachan, antenne de Bretagne (ENS Cachan Bretagne) |
|
|
|
École normale supérieure de Cachan - ENS Cachan |
|
|
| 2: | TEMICS (INRIA - IRISA) |
|
|
|
CNRS : UMR6074 – INRIA – Université de Rennes 1 |
|
|
| 3: | Institut National des Sciences Appliquées de Rennes (INSA Rennes) |
|
|
|
Institut National des Sciences Appliquées (INSA) - Rennes |
|
|
|
|
|
|
|
|
|
| Subject | : | Computer Science/Image Processing |
|
|
| Attached file list to this document: | ||||||||||
|
||||||||||
|
|
|
| hal-00628013, version 1 | |
| http://hal.archives-ouvertes.fr/hal-00628013 | |
| oai:hal.archives-ouvertes.fr:hal-00628013 | |
| From: Vincent Jantet | |
| Submitted on: Friday, 30 September 2011 10:51:14 | |
| Updated on: Tuesday, 8 November 2011 11:58:39 | |
