Translator Disclaimer
4 August 2010 Image matting based high-quality stereo view synthesis
Author Affiliations +
Proceedings Volume 7744, Visual Communications and Image Processing 2010; 77442Z (2010)
Event: Visual Communications and Image Processing 2010, 2010, Huangshan, China
The commercial success and acceptability of 3D technology will critically depend on the overall visual quality of the rendered images. Therefore Depth Image Based Rendering (DIBR) is a crucial component of the 3D system chain. In this paper, we describe a high quality DIBR system for view synthesis. In particular, a procedure is outlined for the processing of the so-called mixed pixels at object boundaries. A Layered Depth Image (LDI) representation of the scene is obtained given an image and corresponding depth map. In the process, all significant mixed pixels in the image are automatically separated into their local foreground and local background. Our results show superior rendering quality, especially at object edges.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hariprasad Kannan, Kiran N. Iyer, Kausik Maiti, Devendra Purbiya, Ajit Bopardikar, and Anshul Sharma "Image matting based high-quality stereo view synthesis", Proc. SPIE 7744, Visual Communications and Image Processing 2010, 77442Z (4 August 2010);


Rendered virtual view image objective quality assessment
Proceedings of SPIE (August 30 2013)
Image Processing on Photon-counting Imaging
Proceedings of SPIE (December 19 1985)
Interactive 3-D Image Display And Analysis
Proceedings of SPIE (July 18 1988)
Image decomposition and enhancement using rank filtering
Proceedings of SPIE (March 10 1998)

Back to Top