Abstract: A method of image processing is disclosed herein, the method comprising: obtaining a first image comprising a first plurality of pixels; obtaining a first segmentation map for the first image, wherein the first segmentation map comprises a first plurality of segmentation values; performing a histogram analysis on the first plurality of pixels, wherein the histogram analysis is weighted based on each pixel's corresponding segmentation value in the first segmentation map, and wherein the histogram analysis comprises determining at least: (a) a median luminance value for pixels that are estimated (e.g., based on their segmentation values) to be part of the background of the first image; and (b) one or more dominant hues for pixels estimated to be part of the background of the first image; and suggesting a first image treatment for the first image based on the determined median luminance value and/or the determined one or more dominant hues.

Abstract: Devices, methods, and non-transitory program storage devices are disclosed to provide for the application of color treatments and/or color normalization operations to digital assets (DAs) in a set of DAs that are to be displayed as part of a multimedia presentation. The determination of the color treatment may be based on comparing one or more characteristics of an audio media item associated with the set of DAs to a corresponding one or more characteristics of a plurality of predetermined color treatments. Color normalization may be applied to the set of DAs prior to the determined color treatment. Techniques disclosed herein may also determine one or more parameters for a multimedia presentation of the set of DAs based on a characteristic of the associated audio media item. The parameters for the multimedia presentation may comprise one or more of: preferred DA sequences, portions, clusters, layouts, themes, transition types, or transition durations.

Abstract: Various implementations disclosed herein include devices, systems, and methods that facilitate the creation of a 3D model for object detection based on a scan of the object. Some implementations provide a user interface that a user interacts with to facilitate a scan of an object to create 3D model of the object for later object detection. The user interface may include an indicator that provides visual or audible feedback to the user indicating the direction that the capturing device is facing relative to the object being scanned. The direction of the capture device may be identified using sensors on the device (e.g., inertial measurement unit (IMU), gyroscope, etc.) or other techniques (e.g., visual inertial odometry (VIO)) and based on the user positioning the device so that the object is in view.

Abstract: Techniques and devices for generating multiple output video variations for an input video based on a shared resource architecture. The shared resource architecture reuses and shares computational and gating results from one or more operations to create the multiple output video variations. The shared resource architecture applies a frame-time normalization of the trimmed and stabilized video to produce a trimmed stabilized normalized video and, thereafter, uses the trimmed stabilized normalized video to precompute one or more video parameters that can be shared with multiple output video variations. The shared resource architecture can then generate multiple output video variations using the shared video parameters.

Abstract: Techniques and devices for creating a Forward-Reverse Loop output video and other output video variations. A pipeline may include obtaining input video and determining a start frame within the input video and a frame length parameter based on a temporal discontinuity minimization. The selected start frame and the frame length parameter may provide a reversal point within the Forward-Reverse Loop output video. The Forward-Reverse Loop output video may include a forward segment that begins at the start frame and ends at the reversal point and a reverse segment that starts after the reversal point and plays back one or more frames in the forward segment in a reverse order. The pipeline for the generating Forward-Reverse Loop output video may be part of a shared resource architecture that generates other types of output video variations, such as AutoLoop output videos and Long Exposure output videos.

Abstract: Techniques and devices for generating multiple output video variations for an input video based on a shared resource architecture. The shared resource architecture reuses and shares computational and gating results from one or more operations to create the multiple output video variations. The shared resource architecture applies a frame-time normalization of the trimmed and stabilized video to produce a trimmed stabilized normalized video and, thereafter, uses the trimmed stabilized normalized video to precompute one or more video parameters that can be shared with multiple output video variations. The shared resource architecture can then generate multiple output video variations using the shared video parameters.

Abstract: Techniques and devices for creating a Forward-Reverse Loop output video and other output video variations. A pipeline may include obtaining input video and determining a start frame within the input video and a frame length parameter based on a temporal discontinuity minimization. The selected start frame and the frame length parameter may provide a reversal point within the Forward-Reverse Loop output video. The Forward-Reverse Loop output video may include a forward segment that begins at the start frame and ends at the reversal point and a reverse segment that starts after the reversal point and plays back one or more frames in the forward segment in a reverse order. The pipeline for the generating Forward-Reverse Loop output video may be part of a shared resource architecture that generates other types of output video variations, such as AutoLoop output videos and Long Exposure output videos.