Coarse-to-fine strategy for efficient cost-volume filtering

Ryosuke Furuta, Satoshi Ikehata, Toshihiko Yamasaki, Kiyoharu Aizawa

Abstract

Cost-volume filtering is one of the most widely known techniques to solve general multi-label problems, however it is problematically inefficient when the label space size is extremely large. This paper presents a coarse-to-fine strategy of the cost-volume filtering that handles efficiently and accurately multi-label problems with a large label space size. Based upon the observation that true labels at the same image coordinate of different scales are highly correlated, we truncate unimportant labels for the cost-volume filtering by leveraging the labeling output of lower scales. Experimental results show that our algorithm achieves much higher efficiency than the original cost-volume filtering while enjoying the comparable accuracy to it.
BibTeX
@inproceedings{furuta2014coarse,
  author = {Ryosuke Furuta and Satoshi Ikehata and Toshihiko Yamasaki and Kiyoharu Aizawa},
  title = {{Coarse-to-fine strategy for efficient cost-volume filtering}},
  booktitle = {ICIP},
  year = {2014},
  doi = {10.1109/icip.2014.7025770},
}

Loading related content...

Figure