Efficiency-enhanced cost-volume filtering featuring coarse-to-fine strategy

被引:0
作者
Ryosuke Furuta
Satoshi Ikehata
Toshihiko Yamaskai
Kiyoharu Aizawa
机构
[1] The University of Tokyo,Department of Information Communication and Engineering
[2] National Institute of Informatics,undefined
来源
Multimedia Tools and Applications | 2018年 / 77卷
关键词
Cost-volume filtering; Markov random field; Multi-labeling problems; Coarse-to-fine;
D O I
暂无
中图分类号
学科分类号
摘要
Cost-volume filtering (CVF) is one of the most widely used techniques for solving general multi-labeling problems based on a Markov random field (MRF). However it is inefficient when the label space size (i.e., the number of labels) is large. This paper presents a coarse-to-fine strategy for cost-volume filtering that efficiently and accurately addresses multi-labeling problems with a large label space size. Based on the observation that true labels at the same coordinates in images of different scales are highly correlated, we truncate unimportant labels for cost-volume filtering by leveraging the labeling output of lower scales. Experimental results show that our algorithm achieves much higher efficiency than the original CVF method while maintaining a comparable level of accuracy. Although we performed experiments that deal with only stereo matching and optical flow estimation, the proposed method can be employed in many other applications because of the applicability of CVF to general discrete pixel-labeling problems based on an MRF.
引用
收藏
页码:12469 / 12491
页数:22
相关论文
共 46 条
[1]  
Achanta R(2012)SLIC Superpixels compared to state-of-the-art superpixel methods IEEE Trans PAMI 34 2274-2281
[2]  
Shaji A(2014)Fast edge-preserving patchmatch for large displacement optical flow IEEE Trans Image Process 23 4996-5006
[3]  
Smith K(2004)An experimental comparison of min-cut/max-flow algorithm for energy minimization in vision IEEE Trans PAMI 26 1124-1137
[4]  
Lucchi A(2001)Fast approximate energy minimization via graph cuts IEEE Trans PAMI 23 1222-1239
[5]  
Fua P(2006)Efficient belief propagation for early vision IJCV 70 41-54
[6]  
Su̇sstrunk S(2006)Convergent tree-reweighted message passing for energy minimization IEEE Trans PAMI 28 1568-1583
[7]  
Bao L(2013)Joint histogram-based cost aggregation for stereo matching IEEE Trans PAMI 35 2539-2545
[8]  
Yang Q(2003)Stereo matching using belief propagation IEEE Trans PAMI 25 787-800
[9]  
Jin H(2008)A comparative study of energy minimization methods for markov random fields with smoothnes-based priors IEEE Trans PAMI 30 1068-1080
[10]  
Boykov Y(2005)Map estimation via agreement on trees: Message-passing and linear-programming approaches IEEE Trans Inf Theory 51 3697-3717