Arnav Bhavsar

Resolution Enhancement of PMD Range Maps

Photonic mixer device (PMD) range cameras are becoming popular as an alternative to algorithmic 3D reconstruction but their main drawbacks are low-resolution (LR) and noise. Recently, some interesting works have stressed on resolution enhancement of PMD range data. These works use high-resolution (HR) CCD images or stereo pairs. But such a system requires complex setup and camera calibration. In contrast, we propose a super-resolution method through induced camera motion to create a HR range image from multiple LR range images. We follow a Bayesian framework by modeling the original HR range as a Markov random field (MRF). To handle discontinuities, we propose the use of an edge-adaptive MRF prior. Since such a prior renders the energy function non-convex, we minimize it by graduated non-convexity.

Range map superresolution-inpainting, and reconstruction from sparse data

Range images often suffer from issues such as low resolution (LR) (for low-cost scanners) and presence of missing regions due to poor reflectivity, and occlusions. Another common problem (with high quality scanners) is that of long acquisition times. In this work, we propose two approaches to counter these shortcomings. Our first proposal which addresses the issues of low resolution as well as missing regions, is an integrated super-resolution (SR) and inpainting approach. We use multiple relatively-shifted LR range images, where the motion between the LR images serves as a cue for super-resolution. Our imaging model also accounts for missing regions to enable inpainting. Our framework models the high resolution (HR) range as a Markov random field (MRF), and uses inhomogeneous MRF priors to constrain the solution differently for inpainting and super-resolution. Our super-resolved and inpainted outputs show significant improvements over their LR/interpolated counterparts. Our second proposal addresses the issue of long acquisition times by facilitating reconstruction of range data from very sparse measurements. Our technique exploits a cue from segmentation of an optical image of the same scene, which constrains pixels in the same color segment to have similar range values. Our approach is able to reconstruct range images with as little as 10% data. We also study the performance of both the proposed approaches in a noisy scenario as well as in the presence of alignment errors.

Resolution Enhancement in Multi-Image Stereo

Under stereo settings, the twin problems of image superresolution (SR) and high-resolution (HR) depth estimation are intertwined. The subpixel registration information required for image superresolution is tightly coupled to the 3D structure. The effects of parallax and pixel averaging (inherent in the downsampling process) preclude a priori estimation of pixel motion for superresolution. These factors also compound the correspondence problem at low resolution (LR), which in turn affects the quality of the LR depth estimates. In this paper, we propose an integrated approach to estimate the HR depth and the SR image from multiple LR stereo observations. Our results demonstrate the efficacy of the proposed method in not only being able to bring out image details but also in enhancing the HR depth over its LR counterpart.

Facial Expression Recognition Using Neural Classifier and Fuzzy Mapping

Facial expression recognition is one of the most important aspects in recognizing human emotions and is a very interesting problem under the broad area of machine vision. In this paper we propose a method for recognition of facial expressions using a neural network classifier followed by a fuzzy mapping. We have tested our algorithm on JAFFE and AT & T database and we have received encouraging results.

Noise adaptive super-resolution from single image via non-local mean and sparse representation

Abstract Super-resolution from a single image is a challenging task, more so, in presence of noise with unknown strength. We propose a robust super-resolution algorithm which adapts itself based on the noise-level in the image. We observe that dependency among the gradient values of relatively smoother patches diminishes with increasing strength of noise. Such a dependency is quantified using the ratio of first two singular values computed from local image gradients. The ratio is inversely proportional to the strength of noise. The number of patches with smaller ratio increases with increasing strength of noise. This behavior is used to formulate some parameters that are used in two ways in a sparse-representation based super-resolution approach: i) in computing an adaptive threshold, used in estimating the sparse coefficient vector via the iterative thresholding algorithm, ii) in choosing between the components representing image details and non-local means of similar patches. Furthermore, our approach constructs dictionaries by coarse-to-fine processing of the input image, and hence does not require any external training images. Additionally, an edge preserving constraint helps in better edge retention. As compared to state-of-the-art approaches, our method demonstrates better efficacy for optical and range images under different types and strengths of noise.

Hierarchical example-based range-image super-resolution with edge-preservation

We propose an example-based approach for enhancing resolution of range-images. Unlike most existing methods on range-image superresolution (SR), we do not employ a colour image counterpart for the range-image. Moreover, we use only a small set of range-images to construct a dictionary of exemplars. Considering the importance of edges in range-image SR, our formulation involves an edge-based constraint to better weight appropriate patches from the dictionary in a sparse-representation framework. Moreover, realizing the need for large up-sampling factors in case of range-images, we follow a hierarchical strategy for estimating the high-resolution range-images. We demonstrate that our strategy yields considerable improvements over the state-of-the-art approaches for range-image SR.

Inpainting Large Missing Regions in Range Images

We propose a technique to in paint large missing regions in range images. Such a technique can be used to restore degraded/occluded range maps. It can also serve to reconstruct dense depth maps from sparse measurements which can speed up the acquisition. Our method uses the visual cue from segmentation of an intensity image registered to the range image. Our approach enforces that pixels in the same segment should have similar range. Our simple strategy involves plane-fitting and local medians over segments to compute local energies for labeling unknown pixels. Our results exhibit high quality in painting with very low errors.

Resolution enhancement for binocular stereo

Traditional stereo algorithms estimate disparity at the same resolution as the observations. In this work we address the problem of estimating disparity and occlusion information at a higher resolution (HR). We draw on the image formation model from the motion super-resolution domain to relate HR disparity and the observations. This approach estimates both the HR disparity and HR intensity. We minimize a suitably constructed cost function using graph cuts and iterated conditional modes (ICM) for disparity and intensity, respectively.

Iterative solvers for image denoising with diffusion models: A comparative study

Abstract In this paper we propose and compare the use of two iterative solvers using the Crank–Nicolson finite difference method, to address the task of image denoising via partial differential equations (PDEs) models such as Regularized Perona–Malik equation or C -model and Bazan model (Bilateral-filter-based model). The solvers which are considered in this paper are the Successive-over-Relaxation (SOR) and an advanced solver known as Hybrid Bi-Conjugate Gradient Stabilized (Hybrid BiCGStab) method. From numerical experiments, it is found that the Crank–Nicolson method with hybrid BiCGStab iterative solver produces better results and is more efficient than SOR and already existing, in terms of MSSIM and PSNR.

Super-resolving a Single Intensity/Range Image via Non-local Means and Sparse Representation

We propose an example-based super-resolution (SR) framework, which uses a single input image and, unlike most of the SR methods does not need an external high resolution (HR) dataset. Our SR approach is based in sparse representation framework, which depends on a dictionary, learned from the given test image across different scales. In addition, our sparse coding focuses on the detail information of the image patches. Furthermore, in the above process we have considered non-local combination of similar patches in the input image, which assist us to improve the quality of the SR result. We demonstrate the effectiveness of our approach for intensity images as well as range images. Contemplating the importance of edges in images of both these modalities, we have added an edge preserving constraint that will maintain the continuity of edge related information to the input low resolution image. We investigate the performance of our approach by rigorous experimental analysis and it shows to perform better than some state-of-the-art SR approaches.