Please use this identifier to cite or link to this item:
https://idr.l4.nitk.ac.in/jspui/handle/123456789/8148
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Balure, C.S. | |
dc.contributor.author | Kini, M.R. | |
dc.contributor.author | Bhavsar, A. | |
dc.date.accessioned | 2020-03-30T10:18:08Z | - |
dc.date.available | 2020-03-30T10:18:08Z | - |
dc.date.issued | 2018 | |
dc.identifier.citation | Communications in Computer and Information Science, 2018, Vol.841, , pp.245-256 | en_US |
dc.identifier.uri | http://idr.nitk.ac.in/jspui/handle/123456789/8148 | - |
dc.description.abstract | Super-resolution (SR) is a technique to improve the resolution of an image from a sequence of input images or from a single image. As SR is an ill-posed inverse problem, it leads to many suboptimal solutions. Since modern depth cameras suffer from low-spatial resolution and are noisy, we present a Gaussian mixture model (GMM) based method for depth image super-resolution (SR). We train GMM from a set of high-resolution and low-resolution (HR-LR) synthetic training depth images to learn the relation between the HR and the LR patches in the form of covariance matrices. We use expectation-maximization (EM) algorithm to converge to an optimal solution. We show the promising results qualitatively and quantitatively in comparison to other depth image SR methods. � Springer Nature Singapore Pte Ltd. 2018. | en_US |
dc.title | GMM based single depth image super-resolution | en_US |
dc.type | Book chapter | en_US |
Appears in Collections: | 2. Conference Papers |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.