4926

High-Speed Stream-Centric Dense Stereo and View Synthesis on Graphics Hardware

Jiangbo Lu, S. Rogmans, G. Lafruit, F. Catthoor
Leuven University, Leuven
IEEE 9th Workshop on Multimedia Signal Processing, 2007. MMSP 2007

@inproceedings{lu2007high,

   title={High-speed stream-centric dense stereo and view synthesis on graphics hardware},

   author={Lu, J. and Rogmans, S. and Lafruit, G. and Catthoor, F.},

   booktitle={Multimedia Signal Processing, 2007. MMSP 2007. IEEE 9th Workshop on},

   pages={243–246},

   year={2007},

   organization={IEEE}

}

Source Source   

828

views

This paper presents an efficient image-based rendering system capable of performing online stereo matching and view synthesis at high speed, completely on the graphics processing unit (GPU). Given two rectified stereo images, our algorithm first extracts the disparity map with a stream-centric dense depth estimation approach. For high-quality view synthesis, multi-label masks are then automatically generated to postprocess occlusions and ambiguously estimated regions adaptively. To allow even faster interactive view generation, an alternative forward warping method is also integrated. The experiments show that photorealistic intermediate views of high image quality are yielded by our algorithm. The optimized implementation also provides the state-of-the-art stereo analysis and view synthesis speed, achieving over 47 fps with 450×375 stereo images and 60 disparity levels on an Nvidia GeForce 7900 graphics card.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: