Computer Science (CS) students, particularly those who are first-generation college students or lack industry exposure, often struggle to see the connections between the courses they take and the wide range of career opportunities available to them. Many have narrow views of career options and limit their vision to a future as a software developer. They may not understand how individual courses, or a combination of them, can prepare them for diverse roles in the computing workforce.

Computer Science (CS) classes teach technical skills, topics and knowledge areas - often without context where they will be used in future classes. Often times, students routinely struggle and ask questions like ''Why am I learning this?'' and ''What value does it hold?''. In addition to not seeing the correlation on topics, students fail to see what applications these concepts could lead to in the future. When asked what they see themselves doing in the future, we have observed that a significant majority of CS majors respond, ''software developer''.

Most required computer science curricula focus on the fundamental concepts of computer science (CS) and do not cover topics regarding professional development. So how do students know and learn why they should get internships, create an online professional presence in places like GitHub, or even craft a compelling resume? In this paper, we present preliminary findings from a pilot project to pair students in CS1 and CS2 classes with industry mentors to increase this awareness, internship placement and ultimately improve student success and graduation rates. We found a positive response from the mentees that participated. Feedback provided by the mentors indicate that a significant majority saw an increase in understanding of these issues after multiple sessions with their paired mentees.

We propose a fast, local denoising method where the Euclidean curvature of the noisy image is approximated in a regularizing manner and a clean image is reconstructed from this smoothed curvature. User preference tests show that when denoising real photographs with actual noise our method produces results with the same visual quality as the more sophisticated, nonlocal algorithms Non-local Means and BM3D, but at a fraction of their computational cost. These tests also highlight the limitations of objective image quality metrics like PSNR and SSIM, which correlate poorly with user preference.

In this paper, we consider an image decomposition model that provides a novel framework for image denoising. The model computes the components of the image to be processed in a moving frame that encodes its local geometry (directions of gradients and level lines). Then, the strategy we develop is to denoise the components of the image in the moving frame in order to preserve its local geometry, which would have been more affected if processing the image directly. Experiments on a whole image database tested with several denoising methods show that this framework can provide better results than denoising the image directly, both in terms of Peak signal-to-noise ratio and Structural similarity index metrics.

In this article we argue that when an image is corrupted by additive noise, its curvature image is less affected by it; i.e., the peak signal-to-noise ratio of the curvature image is larger. We speculate that, given a denoising method, we may obtain better results by applying it to the curvature image and then reconstructing from it a clean image, rather than denoising the original image directly. Numerical experiments confirm this for several PDE-based and patch-based denoising algorithms.

Recently, a number of works have show that patch-based image features can lead to more robust models than their pixel based counterparts. Critical to their success is that natural image patches can be expressed sparsely in appropriately defined dictionaries which can be tuned to a variety of applications. Yu, Sapiro and Mallat [1] demonstrated that estimating image patches from multivariate Gaussians is equivalent to finding sparse representations in a structured overcomplete PCA-based dictionary and can be solved using a straightforward piecewise linear estimator (PLE). In this work we show how a similar PLE can be formulated to fuse images with various linear degradations and different levels of additive noise. We consider the degradation model y = U f + w, in which a given image f has undergone some linear degradation U and is corrupted by additive noise w∼N (0,σ2). Decomposing f into overlapping √ n× √ n vectorized patches fi ∈Rn, i = 1.., I and noting that each patch may have a unique linear degradation Ui and unique additive noise wi, we can express the degraded image patches as yi = Ui fi +wi for i = 1, .., I. Recovering f from y then becomes the problem of recovering fi from yi and rebuilding f from { fi}i=1. In this work we propose a model for recovering f from J images, y j = U j f +w j, j = 1, ..., ,J, where the linear degradations U jand noise levels w j ∼N (0,σj ) may vary amongst images. Following the single image recovery model proposed in [1], we show that given a fixed number of multivariate Gaussians parametrized by their means μk ∈ Rn and covariance matrices Σk ∈ Rn×n, k = 1, ...,K, each patch fi (for i = 1, ..., I) can be estimated by maximizing the log a posteriori probability p( fi|yi , ...,yi ,Σk), which is equivalent to solving

When taking pictures of a dark scene with artificial lighting, ambient light is not sufficient for most cameras to obtain both accurate color and detail information. The exposure bracketing feature usually available in many camera models enables the user to obtain a series of pictures taken in rapid succession with different exposure times; the implicit idea is that the user picks the best image from this set. But in many cases, none of these images is good enough; in general, good brightness and color information are retained from longer-exposure settings, whereas sharp details are obtained from shorter ones. In this paper, we propose a variational method for automatically combining an exposure-bracketed pair of images within a single picture that reflects the desired properties of each one. We introduce an energy functional consisting of two terms, one measuring the difference in edge information with the short-exposure image and the other measuring the local color difference with a warped version of the long-exposure image. This method is able to handle camera and subject motion as well as noise, and the results compare favorably with the state of the art.

In this paper we study finite-difference approximations to the variational problem using the bounded variation (BV) smoothness penalty that was introduced in an image smoothing context by Rudin, Osher, and Fatemi. We give a dual formulation for an upwind finite-difference approximation for the BV seminorm; this formulation is in the same spirit as one popularized by the first author for a simpler, less isotropic, finite-difference approximation to the (isotropic) BV seminorm. We introduce a multiscale method for speeding up the approximation of both Chambolle's original method and of the new formulation of the upwind scheme. We demonstrate numerically that the multiscale method is effective, and we provide numerical examples that illustrate both the qualitative and quantitative behavior of the solutions of the numerical formulations.