Stereo Disparity through Cost Aggregation with Guided Filter
Open Access
- 23 October 2014
- journal article
- Published by Image Processing On Line in Image Processing On Line
- Vol. 4, 252-275
Abstract
Estimating the depth, or equivalently the disparity, of a stereo scene is a challenging problem in computer vision. The method proposed by Rhemann et al. in 2011 is based on a filtering of the cost volume, which gives for each pixel and for each hypothesized disparity a cost derived from pixel-by-pixel comparison. The filtering is performed by the guided filter proposed by He et al. in 2010. It computes a weighted local average of the costs. The weights are such that similar pixels tend to have similar costs. Eventually, a winner-take-all strategy selects the disparity with the minimal cost for each pixel. Non-consistent labels according to left-right consistency are rejected; a densification step can then be launched to fill the disparity map. The method can be used to solve other labeling problems (optical flow, segmentation) but this article focuses on the stereo matching problem.Keywords
This publication has 12 references indexed in Scilit:
- Integral Images for Block MatchingImage Processing On Line, 2014
- Fast cost-volume filtering for visual correspondence and beyond2011
- Guided Image Filtering2010
- Stereo correspondence with compact windows via minimum ratio cycleIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Bilateral filtering for gray and color images2002
- A variable window approach to early visionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- SUSAN—A New Approach to Low Level Image ProcessingInternational Journal of Computer Vision, 1997
- A stereo matching algorithm with an adaptive window: theory and experimentIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- Summed-area tables for texture mappingACM SIGGRAPH Computer Graphics, 1984
- Digital image smoothing and the sigma filterComputer Vision, Graphics, and Image Processing, 1983