Microsoft Technology Licensing, LLC

Vibhav Vineet

Eric J Horvitz

Pedro Urbina Escos

Gavin Jancke

Semiha Ece Kamar Eden

Ishani Chakraborty

Jonathan C Hanzelka

Besmira Nushi

Ondrej Miksik

Vishnu Sai Rao Suresh Lokhande

Michael J Bentley

Tejas Gokhale

Hamid Palangi

Yash Jain

Weiyao Xie

Sameera Lanka

Vicente A Rivera

This document relates to automated analysis of images. One example method involves obtaining an image and text associated with the image, detecting two or more objects in the image, and determining respective locations of the two or more detected objects in the image. The example method also involves determining whether a spatial relationship between the two or more detected objects matches a corresponding spatial relationship expressed by the text based at least on the respective locations of the two or more detected objects. The example method also involves outputting a value reflecting whether the spatial relationship between the two or more detected objects matches the corresponding spatial relationship expressed by the text.

Automated evaluation of spatial relationships in images

A method for virtual object pose rendering includes receiving a digital image of a real-world object in a real-world environment. An imaged pose of the real-world object is estimated based at least in part on a neural radiance model encoding 3D (three-dimensional) spatial data for the real-world object, the neural radiance model derived from a plurality of previously captured digital images of the real-world object. A view of a virtual object corresponding to the real-world object is rendered based at least in part on the neural radiance model, such that the virtual object has a virtual pose consistent with the imaged pose of the real-world object in the digital image.

Virtual pose rendering using neural radiance model

A computing device may receive a plurality of sample slides with various layouts, receive a plurality of augmentations, select one or more augmentations from the plurality of augmentations that are compatible with each other, apply the selected augmentations to the plurality of sample slides to create a plurality of perturbed slides, generate a plurality of slide pairs by combining the plurality of sample slides and the plurality of perturbed slides, filter one or more slide pairs of the plurality of slide pairs that are visually the same, generate the synthetic design dataset including the filtered slide pairs and one or more classes of perturbation that are associated with each of the filtered slide pairs, and train a predictive model using synthetic design dataset for predicting one or more predicted augmentations indicative of one or more layout differences between a pair of slides.

Difference captioning on productivity applications for low vision users

Embodiments of the present invention provide systems, methods, and computer storage media directed to optimizing the accuracy of local feature detection in a variety of physical environments. Homographic adaptation for facilitating personalization of local feature models to specific target environments is formulated in a bilevel optimization framework instead of relying on conventional randomization techniques. Models for extraction of local image features can be adapted according to homography transformations that are determined to be most relevant or optimal for a user's target environment.

Personalized local image features using bilevel optimization

Growing community of inventors

Bellevue, WA, United States of America

Vibhav Vineet