Abstract: A method of object detection in paired imaging includes detecting areas of interest for each image of a set of multi-view images, each detected area of interest having a corresponding initial probability of being an area of interest; determining a matching probability for each detected area of interest across the set of multi-view images such that detected areas of interest from one image of the set of multi-view images are assigned matching probabilities with respect to detected areas of interest of other images of the set of multi-view images; generating a modified probability for each detected area of interest according to one or more object-specific weighting factors and one or more of the matching probabilities for that detected area of interest; adjusting the initial probability of each detected area of interest using the modified probability to generate a refined probability for each detected area of interest; and identifying the detected areas of interest in each image that have refined probabilities

Abstract: The subject matter described herein includes methods, systems, and computer readable media for mask embedding for realistic high-resolution image synthesis. According to one method for mask embedding for realistic high-resolution image synthesis includes receiving, as input, a mask embedding vector and a latent features vector, wherein the mask embedding vector acts as a semantic constraint; generating, using a trained image synthesis algorithm and the input, a realistic image, wherein the realistic image is constrained by the mask embedding vector; and outputting, by the trained image synthesis algorithm, the realistic image to a display or a storage device.