1
Fast Cost-volume Filtering For Visual
Correspondence and Beyond
Asmaa Hosni, Member, IEEE,
Christoph Rhemann,
Michael Bleyer, Member, IEEE,
Carsten Rother, Member, IEEE,
and Margrit Gelautz,Senior Member, IEEE
IEEE Transactions on Pattern Analysis and Machine Intelligence,2013
2
Outline
• Introduction
• Related Work
• Stereo Matching
• Optical Flow
• Interactive Image Segmentation
• Method ：Cost-Volume Filtering
• Applications
• Experimental Results
• Conclusion
3
Introduction
4
Introduction
• Many computer vision tasks can be formulated as labeling
problems.
• Solution : a spatially smooth labeling where label transitions are
aligned with color edges. => very fast edge preserving filter
• A generic and simple framework
• (i) constructing a cost volume
• (ii) fast cost volume filtering
• (iii) winner-take-all label selection
5
Related Work
6
Related Work--Stereo Matching
• Global method
• Energy minimization process (GC,BP,DP,Cooperative)
• Per-processing (mean-sift)
• Accurate but slow
• Local method
• A local support region with winner take all
• Fast but inaccurate.
7
Related Work--Optical Flow
• Optical flow： the pattern of apparent motion caused by the
relative motion between an observer and the scene.
• A vector field subject to Image Brightness Constancy Equation
(IBCE)
• Application： motion detection, object segmentation, motion
compensated encoding, and stereo disparity measurement......
8
Related Work--Optical Flow
• Temporal Persistence
9
Related Work--Optical Flow
• Each flow vector is a label and subpixel accuracy further
increases the label space
• Method：continuous optimization strategies (coarse-to-fine)
• SSD
• Local convolution with oriented Gaussians[13]
• Local convolution with bilateral filter[14]
• Adaptive support weights[15,16]
• Trade off search space (quality) against speed.
[13] D. Tschumperle` and R. Deriche, “Vector-Valued Image Regularization with PDE’s:
A Common Framework for Different Applications,” CVPR, 2003.
[14] J. Xiao, H. Cheng, H. Sawhney, C. Rao, and M. Isnardi,
“Bilateral Filtering-Based Optical Flow Estimation with Occlusion Detection,” ECCV, 2006.
[15] M. Werlberger, T. Pock, and H. Bischof,
“Motion Estimation with Non-Local Total Variation Regularization,” CVPR, 2010.
[16] D. Sun, S. Roth, and M. Black,
“Secrets of Optical Flow Estimation and Their Principles,” CVPR, 2010.
10
Related Work--Interactive Image Segmentation
• Interactive Image Segmentation is a binary labeling problem.
• Goal：Separate the image into foreground and background regions
given some hints by the user.
• Method：
• SNAKE
• Geodesic morphological
operator [8,21]
• Alpha matte [5,22]
[5] K. He, J. Sun, and X. Tang, “Guided Image Filtering,” ECCV, 2010.
[8] A. Criminisi, T. Sharp, and C. Rother,
“Geodesic Image and Video Editing,” ACM Graphics, 2010.
[21] A. Criminisi, T. Sharp, and A. Blake, “GeoS: Geodesic Image Segmentation,”ECCV, 2008.
[22] C. Rhemann, C. Rother, J. Wang, M. Gelautz, P. Kohli, and P. Rott,
“A Perceptually Motivated Online Benchmark for Image Matting,” CVPR, 2009.
11
Cost-volume Filtering
12
Edge-preserving filtering
• Edge-preserving filtering methods
• Weighted Least Square [Lagendijk et al. 1988]
• Anisotropic diffusion [Perona and Malik 1990]
• Bilateral filter [Aurich and Weule 95], [Tomasi and Manduchi 98]
• Digital TV (Total Variation) filter [Chan et al. 2001]
13
Bilateral filter [6]
[6] K. Yoon and S. Kweon, “Adaptive Support-Weight Approach for Correspondence Search,”
IEEE Trans. Pattern Analysis and Machine Intelligence, Apr. 2006.
14
Bilateral filter
• Advantages
• Preserve edges in the smoothing process
• Simple and intuitive
• Non-iterative
• Disadvantages
• Complexity O(Nr2)
• Gradient distortion
Preserves edges,but not gradients
15
Guided filter [5]
[5] K. He, J. Sun, and X. Tang, “Guided Image Filtering,”
Proc. European Conf. Computer Vision, 2010.
16
Guided filter
Bilateral filter does not
have this linear model
17
Guided filter
•
18
Bilateral filter V.S. Guided filter
19
Guided filter
• Edge-preserving filtering
• Non-iterative
Advantages of bilateral filter
• O(1) time, fast and non-approximate
• No gradient distortion
Disadvantages of bilateral filter
20
Cost-volume Filtering
• Label l from
•
• C’ : the filtered cost volume
• i and j : pixel indices.
• Wi,j : The filter weights depend on the guidance image I
•
w=(2r+1)^2
：the mean vector and covariance of I
•
: a smoothness parameter
• U : Identity matrix
•
• Winner take all：
r
k
r
21
Cost-volume Filtering
22
[5] K. He, J. Sun, and X. Tang, “Guided Image Filtering,”
Proc. European Conf. Computer Vision, 2010.
[6] K. Yoon and S. Kweon, “Adaptive Support-Weight Approach for Correspondence Search,”
IEEE Trans. Pattern Analysis and Machine Intelligence, Apr. 2006.
[9] F. Crow. Summed-area tables for texture mapping. SIGGRAPH, 1984.
Cost-volume Filtering
(a) Zoom of the green line in the input image.
(b) Slice of the cost volume for the line(white/black/red: high/low/lowest costs)
(c) The box filter [9]
(d) The joint bilateral filter [6]
(e) The guided filter [5]
(f) Ground-truth labeling
23
Application
24
Stereo Matching
25
Stereo Matching
• Cost computation
•
•
•
: grayscale gradients in x direction
: balances the color and gradient terms
: truncation values
26
Stereo Matching
• Cost computation
•
•
•
: grayscale gradients in x and y direction
: balances the color and gradient terms
: truncation values
• Occlusion detection :
27
Stereo Matching
• Cost computation
•
: grayscale gradients in x and y direction
: balances the color and gradient terms
: truncation values
•
•
• Occlusion detection :
• Postprocessing
1.Scanline filling : the lowest disparity of the spatially closest nonoccluded pixel
2.Median filter :
•
•
: adjust the spatial and color similarity
: normalization factor
28
Stereo Matching
• Alternative—symmetric cost aggregation
• The cost aggregation can be formulated symmetrically for both input images.
• Replace the 3*1 vector Ii in (3) with a 6*1 vector whose entries are given by
the RGB color channels of both Ii and I’i-l .
29
Stereo Matching
• Effect of postprocessing
Disparity map with
invalidated pixels in red
After scanline-based filling
After median filtering
30
Optical flow
• Cost computation
•
•
•
: grayscale gradients in x and y direction
: balances the color and gradient terms
: truncation values
• Postprocessing：Median filter and iteration
31
Optical flow
• Upscale : To find subpixel accurate flow vectors.
• Color of subpixel filled with bicubic interpolation.
32
Interactive Image Segmentation
：foreground F or background B
•
：background color histograms [25]
• b(i)：the bin of pixel i
• Cost computation :
•
(binary labeling) =>
• Five iterations [26]
[25] S. Vicente, V. Kolmogorov, and C. Rother, “Joint Optimization of Segmentation and
Appearance Models,” Proc. IEEE Int’l Conf. Computer Vision, 2009.
[26] C. Rother, V. Kolmogorov, and A. Blake, “Grabcut-Interactive Foreground Extraction
Using Iterated Graph Cuts,” Proc. ACM Siggraph, 2004.
33
Experimental Results
34
Experimental Results
• Device： an Intel Core 2 Quad, 2.4 GHZ PC with GeForce
GTX480 graphics card with 1.5GB of memory from NVIDIA.
• Settings parameters:

: depends on the signal-to-noise ratio of an image
• 0.008 for stereo
• 0.016 for optical flow

• Source : Middlebury http://vision.middlebury.edu/stereo/
35
Stereo Matching
36
Stereo Matching
37
Stereo Matching
38
Stereo Matching
• disparity maps without occlusion filling and postprocessing
(invalidated pixels are black)
39
Stereo Matching
[27] A. Hosni, M. Bleyer, M. Gelautz, and C. Rhemann,
“Local Stereo Matching Using Geodesic Support Weights,” Int’l Conf. Image Processing, 2009.
[6] K. Yoon and S. Kweon,
“Adaptive Support-Weight Approach for Correspondence Search,” PAMI , 2006.
[7] C. Richardt, D. Orr, I. Davies, A. Criminisi, and N. Dodgson,
“Real-Time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral Grid,”ECCV,2010.
40
Stereo Matching
41
Stereo Matching
42
Stereo Matching
• Million Disparity Estimations per second (MDE/s)
• W : width
• H : height
• D : disparity levels
• FPS : number of frames per second
• A larger MDE number means a better performing system.
43
Stereo Matching
44
Stereo Matching
45
Stereo Matching
Table 2. Rankings and run times for selected local stereo methods. Run times in the table
are averaged over the four Middlebury test images.
*The run time in [15] was reported before left-right consistency check in the corresponding
paper. Hence, for fairness, we have multiplied the reported time by a factor of 2.
46
Stereo Matching
47
Optical flow
48
Optical flow
The respective AEE and AAE are given in parentheses (AEE/AAE).
49
Optical flow
Comparison of two sequences with thin structure, where many competitors fail to
preserve flow discontinuities.
(We boosted the colors in the second row from the top for better visualization.)
50
Optical flow
Large displacement flow
• (b)-(e) and (l)-(o) Motion magnitude for
different methods.
• (f), (p) Our flow vectors with the color
coding as in middleburry.
• (h)-(k) Backward warping results using
flow of different methods—the tip of the
foot is correctly recovered by our method.
• Occluded regions cannot be handled by
any method.
51
Interactive Image Segmentation
52
Interactive Image Segmentation
53
Interactive Image Segmentation
Time
error
Our method
2.85 ms
5.3%
GrabCut [26]
300 ms
6.2%
[26] C. Rother, V. Kolmogorov, and A. Blake,
“Grabcut-Interactive Foreground Extraction Using Iterated Graph Cuts,”
Proc. ACM Siggraph, 2004.
54
Experimental Results
• Video
55
Conclusion
56
Conclusion
• Contribution
• Propose a edge-preserving property
• Runtime independent of the filter size
• Achieved both accuracy and efficiency
• Future Work
• Leverage this framework to other application areas
• Process slanted surfaces [32]
[32] M. Bleyer, C. Rhemann, and C. Rother,
“Patchmatch Stereo—Stereo Matching with Slanted Support Windows,”
Proc. British Machine Vision Conf., 2011.