Tomas Yago

University of Rhode Island | URI · Department of Computer Science and Statistics

We introduce Amazon-Berkeley Objects (ABO), a new large-scale dataset of product images and 3D models corresponding to real household objects. We use this realistic, object-centric 3D dataset to measure the domain gap for single-view 3D reconstruction networks trained on synthetic objects. We also use multi-view images from ABO to measure the robus...

In this paper, we present a new approach to estimate the layout of a room from its single image. While recent approaches for this task use robust features learnt from data, they resort to optimization for detecting the final layout. In addition to using learnt robust features, our approach learns an additional ranking function to estimate the final...

Recent shadow detection algorithms have shown initial success on small datasets of images from specific domains. However, shadow detection on broader image domains is still challenging due to the lack of representative annotated training data. In this paper we propose "lazy annotation", an efficient annotation method where an annotator only needs t...

We propose a novel GAN-based framework for detecting shadows in images, in which a shadow detection network (D-Net) is trained together with a shadow attenuation network (A-Net) that generates adversarial training examples. The A-Net modifies the original training images constrained by a simplified physical shadow model and is focused on fooling th...

Single image shadow detection is a very challenging problem because of the limited amount of information available in one image, as well as the scarcity of annotated training data. In this work, we propose a novel adversarial training based framework that yields a high performance shadow detection network (D-Net). D-Net is trained together with an...

The objective of this work is to detect shadows in images. We pose this as the problem of labeling image regions, where each region corresponds to a group of superpixels. To predict the label of each region, we train a kernel Least-Squares Support Vector Machine(LSSVM) for separating shadow and non-shadow regions. The parameters of the kernel and t...

This paper introduces training of shadow detectors under the large-scale dataset paradigm. This was previously impossible due to the high cost of precise shadow annotation. Instead, we advocate the use of quickly but imperfectly labeled images. Our novel label recovery method automatically corrects a portion of the erroneous annotations such that t...

Although previous work has debated whether motion extrapolation is used in multiple object tracking (MOT), here we show that a Kalman filter-based model of motion prediction can simulate tracking accuracy on a trial-by-trial basis. Behavioral data were collected in two experiments manipulating trial duration (exp 1; 4-12s at 8°/s) and item speed (e...

In this paper we present a novel method for shadow removal in single images. For each shadow region we use a trained classifier to identify a neighboring lit region of the same material. Given a pair of lit-shadow regions we perform a region relighting transformation based on histogram matching of luminance values between the shadow region and the...

Does multiple object tracking (MOT) rely on the predicted motion of an object? We addressed this using a continuous tracking paradigm (Exp 1), in which observers tracked 4 of 10 dots moving at 8°/s for 8s. On each 16.6ms frame, all dots had a .025 probability of turning 0°, 15°, 30°, 45°, 60°, 75°, or 90° in either direction (held constant within a...

In this paper we discuss illumination estimation from a single image in general scenes and associate it with the existence of shadow edges, avoiding several pitfalls that burden previous illumination estimation approaches, which rely on associating a parametrization of illumination with the per pixel intensity of shadows or shading. We show a way t...

Vector-borne diseases cause hundreds of thousands of people around the world to suffer debilitating illnesses each year; illnesses such as Lyme Disease, Babesiosis, tick borne encephalitis, Crimean-Congo Hemorrhagic Fever, and Rocky Mountain spotted fever. The spread of these diseases is caused by human-biting ticks. However, in virtually every cas...