Max-planck-gesellschaft Zur F&#xf6;rderung Der Wissenschaften E. V.

Amazon Technologies, Inc.

Imacor Inc.

Nicolas Heron

Michael Julian Black

Matthew Maverick Loper

Eric Rachlin

Alexander Weiss

Oleksandr Vorobiov

Amit Kumar Agrawal

Edward Paul Harhen

David Allen Smith

Steven Douglas Hatch

Harold M Hastings

Scott L Roth

Javier Romero Gonzalez-Nicolas

Larry Davis

Xiaochen Hu

Osama Makansi

Nina Mitra Khosrowsalafi

Wei-Lin Hsiao

Jason Lawrence Gelman

William John O'Farrell

Jonathan Robert Cilley

Evan Lee

Martin Kristiansen

Theodora Hinkle

Techniques are described herein for generating a virtual try-on augmented image. An example method can include A system can access a first two-dimensional model of a target garment. The system can determine a first plurality of shape keypoints for a first part of the first plurality of parts of the image. The system can access a second two-dimensional image of a first user. The system can determine a second plurality of keypoints for a second part of the second plurality of parts of the second two-dimensional image, a second number of the second plurality of keypoints based at least in part on a second predetermined number of keypoints associated with the second part. The system can generate a rendered augmented image of the target garment on the target user.

Model-based augmented image generation

Systems and methods are described for generating images of synthesized bodies wearing a garment. For instance, a source image of a human or mannequin wearing a garment may be submitted to a synthesized human generation system. In response to receiving the source image, the synthesized human generation system may use a classifier to classify the image as depicting one or more body types or orientations. The synthesized human generation system may also apply segmentation to the source image to segment the garment pixels. The synthesized human generation system may then select one or more body generation machine learning models based on the classification of the source image. The synthesized human generation system may utilize the selected machine learning models to generate one or more output images of synthesized bodies that appear to be wearing the garment, using the segmented garment as input.

Generating images of synthesized bodies wearing a garment

Disclosed are systems and techniques for extracting user body shape (e.g., a representation of the three-dimensional body surface) from user behavioral data. The behavioral data may not be explicitly body-shape-related, and can include shopping history, social media likes, or other recorded behaviors of the user within (or outside of) a networked content delivery environment. The determined body shape can be used, for example, to generate a virtual fitting room user interface.

Machine learning systems and methods for extracting user body shape from behavioral data

Disclosed is a method including receiving an input image including a human, predicting, based on a convolutional neural network that is trained using examples consisting of pairs of sensor data, a corresponding body shape of the human and utilizing the corresponding body shape predicted from the convolutional neural network as input to another convolutional neural network to predict additional body shape metrics.

Machine learning systems and methods of estimating body shape from images

Disclosed is a method including receiving visual input comprising a human within a scene, detecting a pose associated with the human using a trained machine learning model that detects human poses to yield a first output, estimating a shape (and optionally a motion) associated with the human using a trained machine learning model associated that detects shape (and optionally motion) to yield a second output, recognizing the scene associated with the visual input using a trained convolutional neural network which determines information about the human and other objects in the scene to yield a third output, and augmenting reality within the scene by leveraging one or more of the first output, the second output, and the third output to place 2D and/or 3D graphics in the scene.

Machine learning systems and methods for augmenting images

Disclosed are computer-implemented methods, systems, and computer program products for displaying superimposed image contours. A first centroid or center-of-mass of a contour extracted from a first image that depicts a moving object as the object appeared at a first time is calculated. A second centroid or center-of-mass of a second contour extracted from a second image that depicts the object as the object appeared at a second time is also calculated. The second image depicts the object in substantially the same plane as the first image. The first and second contours are displayed with the respective first and second centroids or centers-of-mass positioned at a common location. In some implementations, the images are ultrasound images depicting, for example, a human heart. The images can be transgastric short axis views of the human heart.

Superimposed display of image contours

To keep the temperature of an ultrasound probe down, the probe is operated at a low frame rate (with correspondingly low heat generation) for the vast majority of time. Probe operation is only switched to the high frame rate temporarily at times when high temporal resolution is needed, preferably under operator control. The probe is only operated at the high frame rate for a short period of time, during which a burst of images with high temporal resolution is obtained. After capturing the short burst of images, the frame rate is cut back, which reduces the generation of heat.

Temperature management for ultrasound imaging at high frame rates

Growing community of inventors

New York, NY, United States of America

Nicolas Heron