Fast Cost-Volume Filtering for Visual Correspondence and Beyond

被引:558
作者
Hosni, Asmaa [1 ]
Rhemann, Christoph [1 ]
Bleyer, Michael [1 ]
Rother, Carsten [2 ]
Gelautz, Margrit [1 ]
机构
[1] Vienna Univ Technol, Inst Software Technol & Interact Syst, Interact Media Syst Grp, Favoritenstr 9-11-188-2, A-1040 Vienna, Austria
[2] Microsoft Res Cambridge, Cambridge, England
关键词
Stereo matching; optical flow; interactive image segmentation; ENERGY MINIMIZATION; IMAGE;
D O I
10.1109/TPAMI.2012.156
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Many computer vision tasks can be formulated as labeling problems. The desired solution is often a spatially smooth labeling where label transitions are aligned with color edges of the input image. We show that such solutions can be efficiently achieved by smoothing the label costs with a very fast edge-preserving filter. In this paper, we propose a generic and simple framework comprising three steps: 1) constructing a cost volume, 2) fast cost volume filtering, and 3) Winner-Takes-All label selection. Our main contribution is to show that with such a simple framework state-of-the-art results can be achieved for several computer vision applications. In particular, we achieve 1) disparity maps in real time whose quality exceeds those of all other fast (local) approaches on the Middlebury stereo benchmark, and 2) optical flow fields which contain very fine structures as well as large displacements. To demonstrate robustness, the few parameters of our framework are set to nearly identical values for both applications. Also, competitive results for interactive image segmentation are presented. With this work, we hope to inspire other researchers to leverage this framework to other application areas.
引用
收藏
页码:504 / 511
页数:8
相关论文
共 31 条
[1]  
[Anonymous], 2010, P IEEE C COMP VIS PA
[2]  
[Anonymous], 2005, P IEEE C COMP VIS PA
[3]  
[Anonymous], P IEEE C COMP VIS PA
[4]  
[Anonymous], P EUR C COMP VIS
[5]  
[Anonymous], P EUR C COMP VIS
[6]  
[Anonymous], P ACM SIGGRAPH
[7]  
[Anonymous], P EUR C COMP VIS
[8]   PatchMatch Stereo - Stereo Matching with Slanted Support Windows [J].
Bleyer, Michael ;
Rhemann, Christoph ;
Rother, Carsten .
PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2011, 2011,
[9]   Fast approximate energy minimization via graph cuts [J].
Boykov, Y ;
Veksler, O ;
Zabih, R .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (11) :1222-1239
[10]   An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision [J].
Boykov, Y ;
Kolmogorov, V .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2004, 26 (09) :1124-1137