Near real-time Fast Bilateral Stereo on GPUs

THIS PAGE IS UNDER CONSTRUCTION

This page provides additional experimental results concerned with the mapping of the  Fast Bilateral Stereo (FBS) approach on GPUs described in this paper [12]

S. Mattoccia, M. Viti, F. Ries, "Near real-time Fast Bilateral Stereo on the GPU", Best Paper Award at 7th IEEE Workshop on Embedded Computer Vision (ECVW20011), CVPR Workshop, June 20, 2011, Colorado Springs (CO), USA [this is an updated version of the paper: see the NOTE for details]

Compared to the original CPU implementation of FBS, our mapping on a medium-class NVIDIA 460 GTX with CUDA allows us to obtain, with equivalent results, speed-ups > 70X and on a Tesla C2070 speed-ups > 100X.
With the NVIDIA 460 GTX and blocks of size 3x3 the execution time is 65 ms (46 ms with the NVIDIA Tesla) on Tsukuba and 302 ms (201 ms with the NVIDIA Tesla) on Teddy/Cones.
With the NVIDIA 460 GTX and blocks of size 5x5 the execution time is 40 ms (29 ms with the NVIDIA Tesla) on Tsukuba and 178 ms (122 ms with the NVIDIA Tesla) on Teddy/Cones.

FBS is an algorithm that combines the effectiveness of state-of-the-art cost aggregations strategies, that adapt their weights to image content, with the efficiency of fast incremental calculation schemes (i.e. integral images or box filtering) typically deployed by conventional stereo matching algorithms. FBS computes the weights on a block basis and the matching cost on a point-basis; this strategy enables, in both cases, to deploy efficient box-filtering (or integral images) incremental calculation schemes. Additional information, experimental results and software concerned with the FBS approach can be found here.

S. Mattoccia, S. Giardino, A. Gambini, "Accurate and efficient cost aggregation strategy for stereo correspondence based on approximated joint bilateral filtering", Asian Conference on Computer Vision (ACCV2009), September 23- 27, 2009,  Xi'an, China  


NOTE:


This is an updated version the paper. The originally published paper unintentionally failed to describe properly the following paper:

C.Richardt,  D. Orr,  I. Davies, A. Criminisi,  N. A. Dodgson, "Real-time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral Grid", ECCV 2010
In fact, this algorithm computes weights symmetrically and its loss in accuracy, compared to the adaptive weights method, comes primarly  
from the use of greyscale images. 


Acknowledgemetns
We thank NVIDIA Corporation  for their interest in our research and the donation of a Tesla C2070 GPU.


If you are interested in stereo vision, you might find interesting this:

    Stefano Mattoccia
    "Stereo vision: algorithms and applications"
[]
    Extended version of the talk given at the University of Twente, April 1st 2009





References

[1] S. Mattoccia, S. Giardino, A. Gambini, "Accurate and efficient cost aggregation strategy for stereo correspondence based on approximated joint bilateral filtering", Asian Conference on Computer Vision (ACCV2009), September 23- 27, 2009,  Xi'an, China, [Abstract] [Pdf] [Bibtex]

[2] K. Yoon and I. Kweon,  "Adaptive support-weight approach for correspondence search",. IEEE Trans. PAMI, 28(4):650–656, 2006
.
[3] F. Tombari, S. Mattoccia, L. Di Stefano,“Segmentation-based adaptive support for accurate stereo correspondence", IEEE Pacific-Rim Symposium on Image and Video Technology  (PSIVT 2007), Lecture Notes in Computer Science 4872, pp 427-438, Springer 2007, December 17-19, 2007, Santiago, Chile

[4] M. Gerrits and P. Bekaert
, "Local Stereo Matching with Segmentation-based Outlier Rejection", In Proc. Canadian Conf. on Computer and Robot Vision (CRV 2006), pp 66-66, 2006.

[5] S. Kang, R. Szeliski, and J. Chai, "Handling occlusions in dense multi-view stereo", In Proc. Conf. on Computer Vision and Pattern Recognition (CVPR 2001), pages 103–110, 2001.

[6] O. Veksler, "Fast variable window for stereo correspondence using integral images", In Proc. Conf. on Computer Vision and Pattern Recognition (CVPR 2003), pp 556–561, 2003.

[7] D. Scharstein and R. Szeliski, "A taxonomy and evaluation of dense two-frame stereo correspondence algorithms",International Journal of Computer Vision, 47(1/2/3):7-42, April-June 2002 / Microsoft Research Technical Report MSR-TR-2001-81, November 2001

[8] D. Scharstein and R. Szeliski, Middlebury Stereo Vision Page, URL: "vision.middlebury.edu/stereo/"

[9] F. Tombari, S. Mattoccia, L. Di Stefano, E. Addimanda, “Classification and evaluation of cost aggregation methods for stereo correspondence",  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008.

[10] D. Scharstein and C. Pal, "Learning conditional random fields for stereo", In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), Minneapolis, MN, June 2007

[11] S. Mattoccia, "A locally global approach to stereo correspondence", IEEE Workshop on 3D Digital Imaging and Modeling  (3DIM2009), October 3-4, 2009, Kyoto, Japan [Abstract] [Pdf] [Bibtex] [Additional experimental results]

[12] S. Mattoccia, M. Viti, F. Ries, "Near real-time Fast Bilateral Stereo on the GPU", Best Paper Award at 7th IEEE Workshop on Embedded Computer Vision (ECVW20011), CVPR Workshop, June 20, 2011, Colorado Springs (CO), USA [updated version of the paper: see the NOTE for details]






 
Home
 
  

last update on: August 30, 2011