Depth Image Based Rendering: A faithful approach for the disocclusion problem

In this paper we address the disocclusion problem that occurs in Depth Image Based Rendering (DIBR). With a computed background model, the areas which were occluded by foreground objects can be filled with their true color values, in contrast to approximate values as in previous approaches. Our method avoids artifacts that occur with common approaches and can additionally reduce compression artifacts at object boundaries.

[1]  Andrea Fusiello,et al.  Video Objects Segmentation by Robust Background Modeling , 2007, 14th International Conference on Image Analysis and Processing (ICIAP 2007).

[2]  References , 1971 .

[3]  C. Fehn,et al.  Interactive 3-DTV-Concepts and Key Technologies , 2006 .

[4]  Christoph Fehn,et al.  Depth-image-based rendering (DIBR), compression, and transmission for a new approach on 3D-TV , 2004, IS&T/SPIE Electronic Imaging.

[5]  Xiaoyi Jiang,et al.  Synthesizing 3D videos by a motion-conditioned background mosaic , 2008, 2008 19th International Conference on Pattern Recognition.

[6]  Liang Zhang,et al.  Stereoscopic image generation based on depth images for 3D TV , 2005, IEEE Transactions on Broadcasting.