Andrew Rabinovich

TL;DR: An end-to-end 3D reconstruction method for a scene by directly regressing a truncated signed distance function (TSDF) from a set of posed RGB images is presented and semantic segmentation of the 3D model is obtained without significant computation.

TL;DR: A collection of prospectives is presented to provide a glimpse of the techniques that will aid in collecting, managing and utilizing information on complex cellular processes via molecular imaging tools, including: visualizing intracellular protein activity with fluorescent markers, high throughput (and automated) imaging of multilabeled cells in statistically significant numbers, and machine intelligence to analyze subcellular image localization and pattern.

TL;DR: In this article, the authors presented a deep model that can accurately produce dense depth maps given an RGB image with known depth at a very sparse set of pixels, and achieved state-of-the-art performance on both the NYUv2 and KITTI datasets.

TL;DR: A gradient normalization (GradNorm) algorithm that automatically balances training in deep multitask models by dynamically tuning gradient magnitudes is presented, showing that for various network architectures, for both regression and classification tasks, and on both synthetic and real datasets, GradNorm improves accuracy and reduces overfitting across multiple tasks.

TL;DR: A framework for visual grouping that frees the user from the hassles of parameter tuning and model order selection and a new characterization of the space of stabilities for a continuum of segmentations that provides for an efficient sampling scheme.