Abstract: Systems, apparatus, and methods for super-resolution of non-uniform spatial blur. Non-uniform spatial blur presents unique challenges for conventional neural network processing. Existing implementations attempt to handle super-resolution with a “brute force” optimization. Various embodiments of the present disclosure subdivide the super-resolution function into sub-steps. “Unfolding” super-resolution into smaller closed-form functions allows for operation generic plug-and-play convolutional neural network (CNN) logic. Additionally, each step can be optimized with its own step-specific hyper parameters to improve performance.

Abstract: Methods and apparatus for stabilizing image data based on a lens polynomial. Non-rectilinear footage can be captured and rectified in-camera; the rectified images may be stabilized to provide rectified stable video. In one exemplary embodiment, the footage is rectified and stabilized based on a lens polynomial and the camera's own movement. In some variants, the rectified stable video may be stored along with its margin track. In-camera rectified stable video provides several benefits over traditional techniques (e.g., the ability to share rectilinear content from the camera without additional post-processing, as well as reduced file sizes of the shared videos). Lens-aware post-processing can reuse portions of the in-camera rectified stable videos while providing additional benefits (e.g., the ability to re-frame the video in post-production).

Abstract: Systems, apparatus, and methods for encoding telemetry data as audio waveforms. Action cameras may be used to capture telemetry data, which in some applications, may be more useful than its audio/visual media capture. For example, a user may desire the “look-and-feel” of one camera but would like to use the telemetry track information from an action camera. In so-called “piggybacking” operation, the user may rigidly affix the two cameras and use the video track with the telemetry track in post-processing. Unfortunately, time-aligning the two tracks can result in relative drift over time. Various embodiments of the present disclosure transfer telemetry data as data-over-audio. The data-over-audio may be sampled according to the recipient device and recorded at capture. Subsequent post-processing may be performed with the time-aligned tracks.

Abstract: Systems, apparatus, and methods for stabilization and blending of exposures. So-called Electronic Image Stabilization (EIS) techniques use image manipulation software to compensate for camera motion. Unfortunately, existing EIS techniques cannot compensate for artifacts introduced by low shutter speed (e.g., blurs). Various embodiments of the present disclosure generate stabilized images from multiple exposures. In one exemplary embodiment, the stabilized exposures are blended using a linear sum of the color data for each pixel of the image. By stabilizing each exposure and linearly summing the light information, the camera shake can be removed, and the subject motion blur can be controlled. The stabilization and blending techniques enable a mathematical emulation of a selected shutter angle from many high-speed exposures.

Abstract: Systems, apparatus, and methods for color space representation. Unlike television and other passively viewed content, action cameras enable the user to take an active role in content generation/modification. Ideally, image content can be transferred from action cameras to post-processing devices with minimal signal loss (noise introduction), however existing device ecosystems are often bottlenecked by commodity codecs and/or intermediary networks. Various embodiments of the present disclosure use an improved “transport” compression technique to preserve desirable signal codeword and noise codeword relationships for color space representation.

Abstract: An image capture device, having: a housing, a lens snout, a front microphone, a top microphone, and an audio processor. The housing has a top and front housing surface. The lens snout protrudes from the front housing surface. The front microphone mounted within or on the front housing surface and below the lens snout. The top microphone mounted within or on a top housing surface in a position biased toward the front housing surface. The audio processor comprises a memory that is configured to store instructions that when executed cause the audio processor to generate an output audio signal. The top microphone is located at a position to receive direct freestream air flow when the housing is positioned in a pitched forward orientation at a pitched forward angle relative to a vertical axis. The front microphone receives turbulent air flow from the lens snout when the housing is positioned in the pitched forward orientation.

Abstract: An image capture device that includes a housing and a heatsink located partially or completely within the housing. The heatsink comprises a planar surface, a printed circuit board in communication with the heatsink, and a sheet conductor that is a graphite sheet connected to the planar surface of the heatsink and in direct contact with the printed circuit board or components of the printed circuit board.

Abstract: In a video capture system, a virtual lens is simulated when applying a crop or zoom effect to an input video. An input video frame is received from the input video that has a first field of view and an input lens distortion caused by a lens used to capture the input video frame. A selection of a sub-frame representing a portion of the input video frame is obtained that has a second field of view smaller than the first field of view. The sub-frame is processed to remap the input lens distortion to a desired lens distortion in the sub-frame. The processed sub-frame is the outputted.

Abstract: The present disclosure relates to processing a plurality of audio signals. A device receives the plurality of audio signals in the frequency domain and determining an overall attenuation multiplier based on the plurality of audio signals and an overall lookup table that relates decibel values to different overall attenuation multipliers. The device determines an attenuation vector comprising a plurality of bin-specific attenuation multipliers, each bin-specific attenuation multiplier respectively corresponding to a different frequency bin of the plurality of frequency bins. The device scales each bin-specific attenuation value in the attenuation vector with the overall attenuation multiplier, and edits each of the audio signals based on the scaled bin-specific attenuation values in the attenuation vector.

Abstract: Locations in which a person is depicted within video frames may be determined to identify portions of the video frames to be included in a composite video. A background image not including any depiction of the person may be generated, and the identified portions of the video frames may be inserted into the background image to generate the composite video.

Abstract: A highlight moment within a video, music to accompany a looping presentation of the video, and a looping effect for the video may be determined. A segment of the video to be used for the looping presentation of the video may be selected based on highlight moment, the music, and the looping effect. The looping presentation of the video may be generated to have the segment edited based on a style of the looping effect and to include accompaniment of the music.

Abstract: Video information and sensor information may be obtained. The video information may define spherical video content having a progress length. The spherical video content may define visual content viewable from a point a view as a function of progress through the progress length of the spherical video content. The spherical video content may be captured by one or more image capture devices. The sensor information may characterize capture of the spherical video content. A viewing direction for the spherical video content may be determined based on the sensor information and/or other information. The viewing direction may define a direction of view for the spherical video content from the point of view as the function of progress through the progress length of the spherical video content. The spherical video content may be presented on a display based on the viewing direction.

Abstract: An image capture device may be physically connected to a computing device using a data cable. The image capture device may masquerade as an ethernet card to the computing device over the physical connection. The image capture device may communicate with the computing device over the physical connection using a wireless communication protocol.

Abstract: Multiple framings of a video may define different positionings of a viewing window at different moments within the video. The positionings of the viewing window defined by the multiple framings may be used as fixed positionings of the viewing window in a viewing path. The viewing path may define changes in the positioning of the viewing window between the fixed positionings. A presentation of the video may be generated to include the extents of the video within the viewing window.

Abstract: An image capture device with dynamic wind noise compression tuning techniques is described. A technique includes detecting of the presence of wind noise by measuring coherence between at least two microphones. For a compressor, adjusting a default compression threshold and default compression parameters based on the coherence measurements. For each microphone, applying by the compressor the adjusted compression parameters when an audio signal is above the adjusted compression threshold and applying the default compression parameters when the audio signal is below the adjusted compression threshold.