Gopro, Inc.

Alexandre Jenny

Thomas Vuillermet

Yann Renaud Gilquin

Renan Coudray

Antoine Méler

Spherical visual content represented in an image space may be obtained. The spherical visual content may have been captured by image sensor(s) during a time duration. The spherical visual content may include phenomena caused by motion of the image sensor(s) and/or optical components that guide light onto the image sensor(s). A capture path taken by the image sensor(s) during the time duration may be determined. The capture path may reflect positions and orientations of the image sensor(s) during the time duration. A smoothed path may be determined based on the capture path. The smoothed path may have smoother changes in positions and/or orientations than the capture path. The image space may be warped based on a difference between the capture path and the smoothed path. The stabilized visual content may be determined by projecting the spherical visual content represented in the warped image space to a spherical projection space.

Systems and methods for generating stabilized visual content using spherical visual content

Multiple video segments, including multiple frames, may be obtained. The video segments may be time synchronized for at least portions of the video segments captured during a synchronized time period. A first key frame moment may be set with the synchronized time period. A first set of construction parameter values may be determined for the frames captured during the first key frame moment. A first set of spherical images may be constructed using the first set of construction parameter values. A change may be detected in the construction parameter values at a moment in time subsequent to the first key frame moment, which may be identified as a second key frame moment. A second set of construction parameter values may be determined for the frames captured during the second key frame moment. The second set of spherical images may be constructed using the second set of construction parameter values.

Systems and methods for determining key frame moments to construct spherical images

A set of light field sensors may generate light field output signals conveying light field information within fields of view of the set of light field sensors. The generation of the light field outputs signals may be characterized by a subpixel accuracy. The subpixel accuracy may be enabled by a physical link between the set of light field sensors. The fields of view of the set of light field sensors may overlap over an overlap volume. An object may be located within the overlap volume. The light field information characterizing light field emanating from the object may be combined.

Systems and methods for capturing light field of objects

System and methods are disclosed for generating an output video stream from a wide field video stream. The wide field video stream may be created from compiling a plurality of video stream capturing different viewpoints of the same environment simultaneously. Upon selecting a wide field video stream, a first geometric function may be utilized to generate individual intermediate points that correspond to locations in a wide field video stream to be displayed on a particular display space. A second geometric function may be further utilized to generate reference points so that a the pixel on the output video stream are determined from the intermediate points of the wide field video stream of the first geometric function. Upon the execution of the first and second geometric function, an output video stream is generated for display on the determined display space.

Growing community of inventors

Challes les Eaux, France

Alexandre Jenny