Fyusion, Inc.

Martin Saelzle

Stefan Johannes Josef Holzer

Radu Bogdan Rusu

Stephen David Miller

Matteo Munaro

Krunal Ketan Chande

Alexander Jay Bruen Trevor

Pavel Hanchar

Martin Markus Hubert Wawro

Aidas Liaudanskas

Milos Vlaski

Wook Yeon Hwang

Johan Nordin

Nick Stetco

Rodrigo Ortiz Cayon

Nico Gregor Sebastian Blodow

Abhishek Kar

George Haber

Shuichi Tsutsumi

Rodrigo Ortiz-Cayon

Blake McConnell

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

Images may be captured at an image capture device mounted on an image capture device gimbal capable of rotating the image capture device around a nodal point in one or more dimensions. Each of the plurality of images may be captured from a respective rotational position. The images may be captured by a designated camera that is not located at the nodal point in one or more of the respective rotational positions. A designated three-dimensional point cloud may be determined based on the plurality of images. The designated three-dimensional point cloud may include a plurality of points each having a respective position in a virtual three-dimensional space.

Enclosed multi-view visual media representation

Images of an undercarriage of a vehicle may be captured via one or more cameras. A point cloud may be determined based on the images. The point cloud may includes points positioned in a virtual three-dimensional space. A stitched image may be determined based on the point cloud by projecting the point cloud onto a virtual camera view. The stitched image may be stored on a storage device.

Vehicle undercarriage imaging

Various embodiments of the present invention relate generally to mechanisms and processes relating to artificially rendering images using viewpoint interpolation and extrapolation. According to particular embodiments, a method includes applying a transform to estimate a path outside the trajectory between a first frame and a second frame, where the first frame includes a first image captured from a first location and the second frame includes a second image captured from a second location. The process also includes generating an artificially rendered image corresponding to a third location positioned on the path. The artificially rendered image is generated by interpolating a transformation from the first location to the third location and from the third location to the second location, gathering image information from the first frame and the second frame by transferring first image information from the first frame to the third frame and second image information from the second frame to the third frame, and combining the first image information and the second image information.

Artificially rendering images using viewpoint interpolation and extrapolation

Various embodiments of the present invention relate generally to systems and processes for transforming a style of video data. In one embodiment, a neural network is used to interpolate native video data received from a camera system on a mobile device in real-time. The interpolation converts the live native video data into a particular style. For example, the style can be associated with a particular artist or a particular theme. The stylized video data can viewed on a display of the mobile device in a manner similar to which native live video data is output to the display. Thus, the stylized video data, which is viewed on the display, is consistent with a current position and orientation of the camera system on the display.

Live style transfer on a mobile device

Various embodiments of the present invention relate generally to systems and methods for artificially rendering images using viewpoint interpolation and extrapolation. According to particular embodiments, a method includes moving a set of control points perpendicular to a trajectory between a first frame and a second frame, where the first frame includes a first image captured from a first location and the second frame includes a second image captured from a second location. The set of control points is associated with a layer and each control point is moved based on an associated depth of the control point. The method also includes generating an artificially rendered image corresponding to a third location outside of the trajectory by extrapolating individual control points using the set of control points for the third location and extrapolating pixel locations using the individual control points.

Various embodiments of the present invention relate generally to systems and processes for artificially rendering images using interpolation of tracked control points. According to particular embodiments, a set of control points is tracked between a first frame and a second frame, where the first frame includes a first image captured from a first location and the second frame includes a second image captured from a second location. An artificially rendered image corresponding to a third location is then generated by interpolating individual control points for the third location using the set of control points and interpolating pixel locations using the individual control points. The individual control points are used to transform image data.

Artificially rendering images using interpolation of tracked control points

Various embodiments of the present invention relate generally to systems and methods for artificially rendering images using viewpoint interpolation and/or extrapolation. According to particular embodiments, a transformation between a first frame and a second frame is estimated, where the first frame includes a first image captured from a first location and the second frame includes a second image captured from a second location. An artificially rendered image corresponding to a third location positioned on a trajectory between the first location and the second location is then generated by interpolating a transformation from the first location to the third location and from the third location to the second location and gathering image information from the first frame and the second frame by transferring first image information from the first frame to the third frame based on the interpolated transformation and second image information from the second frame to the third frame based on the interpolated transformation. The first image information and the second image information are then combined. If an occlusion is created by a change in layer placement between the first frame and second frame, this occlusion is detected and missing data is replaced to fill the occlusion.

Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. According to particular embodiments, the spatial relationship between multiple images and video is analyzed together with location information data, for purposes of creating a representation referred to herein as a surround view for presentation on a device. A real object can be tracked in the live image data for the purposes of creating a surround view using a number of tracking points. As a camera is moved around the real object, virtual objects can be rendered into live image data to create synthetic images where a position of the tracking points can be used to position the virtual object in the synthetic image. The synthetic images can be output in real-time. Further, virtual objects in the synthetic images can be incorporated into surround views.

Live augmented reality using tracking

Provided are mechanisms and processes for augmenting multi-view image data with synthetic objects using inertial measurement unit (IMU) and image data. In one example, a process includes receiving a selection of an anchor location in a reference image for a synthetic object to be placed within a multi-view image. Movements between the reference image and a target image are computed using visual tracking information associated with the multi-view image, device orientation corresponding to the multi-view image, and an estimate of the camera's intrinsic parameters. A first synthetic image is then generated by placing the synthetic object at the anchor location using visual tracking information in the multi-view image, orienting the synthetic object using the inverse of the movements computed between the reference image and the target image, and projecting the synthetic object along a ray into a target view associated with the target image. The first synthetic image is overlaid on the target image to generate an augmented image from the target view.

Growing community of inventors

San Francisco, CA, United States of America

Martin Saelzle