Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
4 results
Search Results
Item Single depth image super-resolution via high-frequency subbands enhancement and bilateral filtering(Institute of Electrical and Electronics Engineers Inc., 2016) Balure, C.S.; Ramesh Kini, M.; Bhavsar, A.This paper addresses the problem of super-resolution (SR) from a single low-resolution (LR) depth image to a high-resolution (HR) depth image. A simple yet effective method has been proposed using Discrete Wavelet Transform (DWT), Stationary Wavelet Transform (SWT), and by utilizing the gradient information of the interpolated LR image. We propose an intermediate stage to enhance the high-frequency subbands to recover the HR image for both noiseless and noisy scenarios. The proposed method has been validated on Middlebury dataset for different upsampling factors (i.e. 2, 4, 8) and is shown to be superior when compared with some related DWT and SWT based SR methods. We also demonstrate encouraging performance of the approach on noisy depth images. © 2016 IEEE.Item Depth image super-resolution with local medians and bilateral filtering(Institute of Electrical and Electronics Engineers Inc., 2016) Balure, C.S.; Ramesh Kini, M.; Bhavsar, A.In this paper, we propose an approach for depth image super-resolution (SR). Given a noisy low resolution (LR) depth image and its corresponding registered high resolution (HR) colour image, our approach improves the resolution of the LR image while suppressing noise. We use the segmentation of HR colour images as a cue for depth image super-resolution. Our method begins with a highly over-segmented color image (using well-known segmentation approaches such as mean shift (MS) or simple linear iterative clustering (SLIC), and an interpolated LR depth image. We then use a combination of the local medians in the depth image (corresponding to the colour segments) and bicubic interpolation, followed by bilateral filtering to compute the SR depth image. We performed experiments for higher magnification factors 4, 8 using the Middlebury depth image dataset and evaluate the SR performance using the PSNR and SSIM metrics. The experimental results show that proposed method (including some variants), while being relatively simplistic, shows an average improvement of 1.2dB and 1.7dB on noiseless and noisy data respectively, over the popular method of guided image filtering (GIF) for upsampling factor 8. © 2016 IEEE.Item Local segment-based dense depth reconstruction from very sparsely sampled data(Institute of Electrical and Electronics Engineers Inc., 2017) Balure, C.S.; Bhavsar, A.; Ramesh Kini, M.R.In this paper, we propose two relatively simplistic and efficient methods for depth reconstruction from very sparsely sampled random depth data. Both the proposed approaches exploit the segmentation cue from a registered colour image of the same scene. The first approach which we term as plane fitting depth reconstruction (PFitDR), involves cost computations on plane-fitted depth values over local segments. The second approach, which we call median filled depth reconstruction (MFillDR) is an even simpler method, wherein the reconstruction is carried out using computation of median of depth values over local segments. We demonstrate dense reconstruction from very less number of available depth points (e.g. as low as 1%). Our methods favorably compare with a recent related state-of-the-art method, both qualitatively as well as quantitatively in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) indices. © 2017 IEEE.Item GMM based single depth image super-resolution(Springer Verlag service@springer.de, 2018) Balure, C.S.; Ramesh Kini, M.R.; Bhavsar, A.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.