Abstract: Methods and apparatus for post-processing in-camera stabilized video. Embodiments of the present disclosure reconstruct and re-stabilize an in-camera stabilized video to provide for improved stabilization (e.g., a wider crop, etc.). In-camera sensor data may be stored and used to re-calculate orientation metadata in post-production. In-camera stabilization provides several benefits (e.g., the ability to share stabilized videos from the camera without additional post-processing as well as reduced file sizes of the shared videos). Camera-aware post-processing can reuse portions of the in-camera stabilized videos while providing additional benefits (e.g., the ability to regenerate the original captured videos in post-production and re-stabilize the videos). Camera-aware post-processing can also improve orientation metadata and remove sensor error. The disclosed techniques also enable assisted optical flow-based stabilization using the refined metadata.

Abstract: Modular lens assemblies and mounting systems are disclosed. A modular lens assembly includes a removable portion and a fixed portion. The removable portion includes a first lens stack configured to produce a near-collimated ray path or a collimated ray path. The fixed portion includes a second lens stack configured to receive the near-collimated ray path or the collimated ray path from the removable portion. The modular lens assembly may be implemented in an image capture device. An image sensor of the image capture device is positioned at an end of the modular lens assembly. The image sensor is configured to capture images based on light incident on the image sensor through the first lens stack and the second lens stack such that the light incident on an outer lens of the first lens stack is refracted through the second lens stack to the image sensor.

Abstract: An image capture device may include an electronic display. A graphical user interface may be presented on the electronic display. The graphical user interface may provide a dynamic view of the settings of the image capture device. Settings shown within the graphical user interface may dynamically change to show the available settings of the image capture device.

Abstract: An image capture apparatus may include an image sensor, a motion sensor, and an auto-exposure unit. The auto-exposure unit may obtain an input image captured during an exposure interval and corresponding motion data indicating motion of the image capture apparatus during the exposure interval. The auto-exposure unit may obtain image information-amount data for the input image. The auto-exposure unit may obtain derivative information-amount data based on the information-amount data and a candidate exposure adjustment. The auto-exposure unit may obtain an information-amount maximizing exposure interval based on the information-amount data and the derivative information-amount data. The image capture apparats may control the image sensor to obtain a subsequent input image signal representing a subsequent input image captured during the information-amount maximizing exposure interval, and output or store information representing the subsequent input image.

Abstract: Image capture devices and methods may be used to pre-buffer media storage. The pre-buffering method includes recording an image capture segment of a variable bitrate input stream in a circular buffer. The circular buffer includes a number of recordable segments. The method includes recording a next image capture segment in a next adjacent recordable segment of the circular buffer if the next adjacent recordable segment of the predetermined number of recordable segments is available. The method includes overwriting an oldest recordable segment if the next adjacent recordable segment of the predetermined number of recordable segments is not available.

Abstract: Automatic exposure with simulated histograms may include obtaining a noise-blur exposure duration value in accordance with a minimal simulated noise-blur cost value obtained in accordance with simulated noise data and simulated blur data, obtaining a saturation exposure value in accordance with a minimal simulated saturation cost value obtained in accordance with simulated black saturation data and simulated white saturation data, comparing the noise-blur exposure duration value and the saturation exposure value, and obtaining a target gain value and a target exposure duration value based on the comparison, wherein the comparing may include obtaining the target exposure duration value in accordance with a minimal simulated blur-saturation cost value obtained in accordance with the simulated blur data and the simulated black saturation data or in accordance with a minimal simulated noise-saturation cost value obtained in accordance with the simulated noise data and the simulated white saturation data.

Abstract: A video may include visual content having a field of view. Extents of the visual content within a viewing window may be presented on an electronic display. For a time point in the video, the video may be framed by positioning the viewing window within the field of view of the visual content. The framing of the video at the time point in the video may be extended to a duration in the video. The extended framing of the video over the duration may be presented within a graphical user interface.

Abstract: Systems, apparatus, and methods for augmenting dense depth maps using sparse data. Various embodiments combine single-image depth estimation (SIDE) techniques with structure-from-motion techniques for improved depth accuracy. In some examples, a machine learning (ML) model is used to generate a dense depth map based on one or more frames/images of a video. Structure-from-motion (SfM) analysis is performed on the video to determine depth information from camera movement in the video. The structure-from-motion techniques may generate more accurate data than the ML model, however, the data from the ML model may be denser compared with the SFM depth data. The dense ML model depth map may be augmented by the SFM depth data. Augmentation may include fitting the relative depths determined by the ML model depth map to the absolute depth in the SFM data resulting in more accurate dense depth information.

Abstract: A user may carry a computing device. Communication between the computing device and an image capture device may be used to determine when the image capture device becomes separated from the computing device. When the image capture device becomes separated from the computing device, the operation(s) of the image capture device may be changed to assist the user in locating the image capture device. Information on location of the image capture device may be provided to the user through the computing device to assist the user in locating the image capture device.

Abstract: Multiple punchouts of a video may be presented based on multiple viewing windows. The video may include visual content having a field of view. Multiple viewing windows may be determined for the video, with individual viewing window defining a set of extents of the visual content. Different punchouts of the visual content may be presented based on the different viewing windows. Individual punchout of the visual content may include the set of extents of the visual content defined by corresponding viewing window.

Abstract: Systems, apparatus, and methods for encoding timelapse videos. Timelapse photography involves capturing a sequence of images at set intervals over a period of time and then playing them back at a higher speed. Unfortunately, timelapse photography introduces a variety of problems that conventional photography does not have. Exemplary embodiments capture light information in a power efficient manner and encode them in bulk (a video segment at a time). In some variants, the light information may be stored as raw data; in other variants, the light information may be stored as compressed images. The segment-based encoding has the additional benefit of creating identifiable breakpoints that allow for file access without interfering with the capture; this may be used to check the status of the video mid-recording.

Abstract: An image signal processor accesses raw images from an image sensor. The image signal processor obtains adaptive acquisition control data for the raw images. The adaptive acquisition control data comprises at least one of a luminance value, a contrast value, a gain value, an exposure value, or a white balance value. The image signal processor obtains, in accordance with the adaptive acquisition control data, an indication of whether to use a star trails scene classification for the raw images. The image signal processor transmits, to buffers for storing data in accordance with the raw images, the indication of whether to use the star trails scene classification.

Abstract: Systems, apparatus, and methods for adding post-processing motion blur to video. Conventional post-processing techniques relied on the filmmaker to select and stage their shots. Different motion blur techniques were designed to fix certain types of footage. Vector blur is one technique that “smears” pixel information in the direction of movement. Frame interpolation and stacking attempts to create motion blur by stacking interpolated frames together. Each technique has its own set of limitations. Various embodiments use a combination of motion blur techniques in post-processing for better, more realistic outcomes with faster/more efficient rendering times. In some cases, this may enable adaptive quality post-processing that may be performed in mobile/embedded ecosystems.

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 using 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.