Fyusion, Inc.

Rodrigo Ortiz-Cayon

Stefan Johannes Josef Holzer

Matteo Munaro

Pavel Hanchar

Aidas Liaudanskas

Krunal Ketan Chande

Srinivas Rao

Radu Bogdan Rusu

Abhishek Kar

Martin Saelzle

Pantelis Kalogiros

Martin Markus Hubert Wawro

Mike Penz

Julius Santiago

Nico Gregor Sebastian Blodow

Ioannis Spanos

Yusuke Tomoto

Santi Arano

Jai Chaudhry

Nishant Rai

Raul Dronca

Tobias Bertel

Christian Richardt

Ashley Wakefield

Josh Faust

Santiago Arano Perez

Tanvir Parhar

A plurality of images of an object and a background may be captured. Three-dimensional representations of the background and the object may be generated based on the captured images. A synthetic image of the object and the background may be rendered. The synthetic image may depict a two-dimensional view of the object having a novel viewpoint different from the viewpoints of the captured images. A corrected synthetic image may be generated. The corrected synthetic image may be stored on a storage medium.

Automatically generating synthetic images from novel viewpoints

One or more two-dimensional images of a three-dimensional object may be analyzed to estimate a three-dimensional mesh representing the object and a mapping of the two-dimensional images to the three-dimensional mesh. Initially, a correspondence may be determined between the images and a UV representation of a three-dimensional template mesh by training a neural network. Then, the three-dimensional template mesh may be deformed to determine the representation of the object. The process may involve a reprojection loss cycle in which points from the images are mapped onto the UV representation, then onto the three-dimensional template mesh, and then back onto the two-dimensional images.

Weak multi-view supervision for surface mapping estimation

Images of an object may be captured via a camera at a mobile computing device at different viewpoints. The images may be used to identify components of the object and to identify damage estimates estimating damage to some or all of the components. Capture coverage levels corresponding with the components may be determined, and then recording guidance may be provided for capturing additional images to increase the capture coverage levels.

Multi-view visual data damage detection

Images of an object may be captured at a computing device. Each of the images may be captured from a respective viewpoint based on image capture configuration information identifying one or more parameter values. A multiview image digital media representation of the object may be generated that includes some or all of the images of the object and that is navigable in one or more dimensions.

Damage detection from multi-view visual data

Damage to an object such as a vehicle may be detected and presented based at least in part on image data. In some configurations, image data may be detected by causing the object to pass through a gate or portal on which cameras are located. Alternatively, or additionally, image data may be selected by a user operating a camera and moving around the object. The cameras may capture image data, which may be combined and analyzed to detect damage. Some or all of the image data and/or analysis of the image data may be presented in a viewer, which may allow a user to perform actions such as navigating around the object in a virtual environment, identifying and viewing areas of the object where damage has been detected, and accessing the results of the analysis.

Multi-view interactive digital media representation viewer

Novel images may be generated using an image generator implemented on a processor. The image generator may receive as input neural features selected from a neural texture atlas. The image generator may also receive as input one or more position guides identifying position information for a plurality of input image pixels. The novel images may be evaluated using an image discriminator to determine a plurality of optimization values by comparing each of the plurality of novel images with a respective one of a corresponding plurality of input images. Each of the novel images may be generated from a respective camera pose relative to an object identical to that of the respective one of the corresponding plurality of input images. The image generator and the neural features may be updated based on the optimization values and stored on a storage device.

Deferred neural rendering for view extrapolation

Growing community of inventors

San Francisco, CA, United States of America

Rodrigo Ortiz-Cayon