Amazon Technologies, Inc.

Siddhartha Chandra

Amit Kumar Agrawal

Ambrish Tyagi

James Rehg

Shashank Tripathi

Apoorv Chaudhri

Prakash Ramu

Visesh Uday Kumar Chari

Visesh Chari

Antonio Criminisi

Ram Sever

Ita Lifshitz

Rajesh Gautam

Anantharanga Prithviraj

Anna Shtengel

Ayush Sharma

Sigal Raab

Viveka Kulharia

F Noam Sorek

Gal Levi

Described are systems and methods that use one or more two-dimensional ('2D') body images of a body to determine body fat measurements of that body. For example, a standard 2D camera of a portable device, such as a cell phone, tablet, laptop, etc., may be used to generate one or more 2D body images of a user. Those 2D body images, or image, may be processed using the disclosed implementations to determine a body fat measurement of the body represented in the image.

Body fat measurements from a two-dimensional image

Described are systems and methods directed to generation and subsequent update of a dimensionally accurate body model of a body, such as a human body, based on two-dimensional ('2D') images of at least a portion of that body and/or face images of a face of the body. A user may use a 2D camera, such as a digital camera typically included in many of today's portable devices (e.g., cell phones, tablets, laptops, etc.) to produce body images that are used to generate a body model of the body of the user. Subsequently, the body model may be updated based on a face image of the face of the user, without requiring the user to provide another body image.

Body model composition update from two-dimensional face images

Techniques are generally described for object detection in image data. First image data comprising a three-dimensional model representing an object may be received. First background image data comprising a first plurality of pixel values may be received. A first feature vector representing the three-dimensional model may be generated. A second feature vector representing the first plurality of pixel values of the first background image data may be generated. A first machine learning model may generate a transformed representation of the three-dimensional model using the first feature vector. First foreground image data comprising a two-dimensional representation of the transformed representation of the three-dimensional model may be generated. A frame of composite image data may be generated by combining the first foreground image data with the first background image data.

Generation of synthetic image data using three-dimensional models

Devices and techniques are generally described for weakly-supervised object segmentation in image data. In various examples, a first frame of image data may be received. The first frame may include a first bounding box surrounding a first set of pixels, wherein first subset of pixels of the first set of pixels represent a first object of a first class and wherein second subset of pixels of the first set of pixels represent background image data. Cross-entropy loss may be determined for the first set of pixels. In some examples, a spatial attention map may be determined for the first set of pixels. In further examples, parameters of a convolutional neural network may be determined by modulating the cross-entropy loss for the first set of pixels using the spatial attention map. The convolutional neural network may be used to generate a segmentation map.

Segmentation using attention-weighted loss and discriminative feature learning

Techniques are generally described for object detection in image data. First image data comprising a first plurality of pixel values representing an object and a second plurality of pixel values representing a background may be received. First foreground image data and first background image data may be generated from the first image data. A first feature vector representing the first plurality of pixel values may be generated. A second feature vector representing a first plurality of pixel values of second background image data may be generated. A first machine learning model may determine a first operation to perform on the first foreground image data. A transformed representation of the first foreground image data may be generated by performing the first operation on the first foreground image data. Composite image data may be generated by compositing the transformed representation of the first foreground image data with the second background image data.

Generation of synthetic image data for computer vision models

Growing community of inventors

Santa Clara, CA, United States of America

Siddhartha Chandra