Monocular depth estimation and image deblurring are two fundamental tasks in computer vision, given their crucial role understanding 3D scenes. Performing any of them by relying on a single is an ill-posed problem. The recent advances the field Deep Convolutional Neural Networks (DNNs) have revolutionized many including deblurring. When it comes to using defocused images, recovery All-in-Focus ...

The ability to retrieve the complex-valued, generalized pupil function of an imaging system from undersampled measurements of the defocused system point spread function (PSF) is examined through numerical simulations. The ability to do so degrades as the detector pixel pitch increases when using a fixed number of PSF measurements. Two strategies for obtaining better results with undersampled da...

We present the framework for convergent beam Bragg ptychography, and, using simulations, we demonstrate that nanocrystals can be ptychographically reconstructed from highly convergent x-ray Bragg diffraction. The ptychographic iterative engine is extended to three dimensions and shown to successfully reconstruct a simulated nanocrystal using overlapping raster scans with a defocused curved beam...

We propose a polarizer-free liquid crystal display (LCD) with an electrically switchable microlens array. The incident lights are controlled to focused or defocused states by index matching of the lens polymer and LC layer. By adopting two light-blocking masks that have a circular stop pattern and the complementary open pattern, the LCD was able to realize the entire gray scale. Additionally, t...

A MAP-MRF based scheme is proposed for simultaneous recovery of the depth and the focused image of a scene from two defocused images. The space-variant blur parameter and the focused image of the scene are both modeled as MRFs and their MAP estimates are obtained using simulated annealing. The performance of the proposed scheme is tested on synthetic as well as real data and the estimates of th...

A novel semi-blind defocused image deconvolution technique is proposed, which is based on multivariate local polynomial regression and iterative Wiener filtering. In this technique, firstly a multivariate local polynomial regression model is trained in wavelet domain to estimate defocus parameter. After obtaining the point spread function (PSF ) parameter, iterative wiener filter is adopted to ...