Abstract
Several new algorithms for visual correspondence based on graph cuts [7, 14, 17] have recently been developed. While these methods give very strong results in practice, they do not handle occlusions properly. Specifically, they treat the two input images asymmetrically, and they do not ensure that a pixel corresponds to at most one pixel in the other image. In this paper, we present a new method which properly addresses occlusions, while preserving the advantages of graph cut algorithms. We give experimental results for stereo as well as motion, which demonstrate that our method performs well both at detecting occlusions and computing disparities.
Keywords
Computer scienceArtificial intelligencePixelComputer visionGraphCutImage (mathematics)Theoretical computer scienceImage segmentation
Affiliated Institutions
Related Publications
Global optimization using embedded graphs
One of the challenges of computer vision is that the information we seek to extract from images is not even defined for most images. Because of this, we cannot hope to find a si...
A variable window approach to early vision
Early vision relies heavily on rectangular windows for tasks such as smoothing and computing correspondence. While rectangular windows are efficient, they yield poor results nea...
Fast approximate energy minimization via graph cuts
Many tasks in computer vision involve assigning a label (such as disparity) to every pixel. A common constraint is that the labels should vary smoothly almost everywhere while p...
Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images
In this paper we describe a new technique for general purpose interactive segmentation of N-dimensional images. The user marks certain pixels as "object" or "background" to prov...
Seam carving for content-aware image resizing
Effective resizing of images should not only use geometric constraints, but consider the image content as well. We present a simple image operator called seam carving that suppo...
Publication Info
- Year
- 2002
- Type
- article
- Volume
- 2
- Pages
- 508-515
- Citations
- 1126
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
1126
OpenAlex
Cite This
Vladimir Kolmogorov,
Ramin Zabih
(2002).
Computing visual correspondence with occlusions using graph cuts.
, 2
, 508-515.
https://doi.org/10.1109/iccv.2001.937668
Identifiers
- DOI
- 10.1109/iccv.2001.937668