A constant-space belief propagation algorithm for stereo matching

Qingxiong Yang, Liang Wang, Narendra Ahuja
University of Illinois at Urbana Champaign
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010 (June 2010), pp. 1458-1465.


   title={A constant-space belief propagation algorithm for stereo matching},

   author={Yang, Q. and Wang, L. and Ahuja, N.},

   booktitle={Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on},






Download Download (PDF)   View View   Source Source   



In this paper, we consider the problem of stereo matching using loopy belief propagation. Unlike previous methods which focus on the original spatial resolution, we hierarchically reduce the disparity search range. By fixing the number of disparity levels on the original resolution, our method solves the message updating problem in a time linear in the number of pixels contained in the image and requires only constant memory space. Specifically, for a 800 x 600 image with 300 disparities, our message updating method is about 30x faster (1.5 second) than standard method, and requires only about 0.6% memory (9 MB). Also, our algorithm lends itself to a parallel implementation. Our GPU implementation (NVIDIA Geforce 8800GTX) is about 10x faster than our CPU implementation. Given the trend toward higher-resolution images, stereo matching using belief propagation with large number of disparity levels as efficient as the small ones makes our method future-proof. In addition to the computational and memory advantages, our method is straightforward to implement.
No votes yet.
Please wait...

* * *

* * *

* * *

HGPU group © 2010-2023 hgpu.org

All rights belong to the respective authors

Contact us: