Fast and Efficient Dense Variational Stereo on GPU

Julien Mairal, Renaud Keriven, Alexandre Chariot
CERTIS, ENPC, 77455 Marne-la-Vallee cedex 2 France
Third International Symposium on 3D Data Processing, Visualization, and Transmission, 2006, p.97-104


   title={Fast and efficient dense variational stereo on GPU},

   author={Mairal, J. and Keriven, R. and Chariot, A.},

   booktitle={3D Data Processing, Visualization, and Transmission, Third International Symposium on},






Download Download (PDF)   View View   Source Source   



Thanks to their high performance and programmability, the latest graphics cards can now be used for scientific purpose. They are indeed very efficient parallel single instruction multiple data (SIMD) machines. This new trend is called general purpose computation on graphics processing unit (GPGPU). Regarding the stereo problem, variational methods based on deformable models provide dense, smooth and accurate results. Nevertheless, they prove to be slower than usual disparity-based approaches. In this paper, we present a dense stereo algorithm, handling occlusions, using three cameras as inputs and entirely implemented on a graphics processing unit (GPU). Experimental speedups prove that our approach is efficient and perfectly adapted to the GPU, leading to nearly video frame rate reconstruction.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: