Abstract: This disclosure provides systems, methods, and devices for image signal processing that provide transitioning between cameras of different dynamic range capability. In a first aspect, a method of image processing includes receiving first image data comprising first image frames from a first camera having a first dynamic range capability and second image data comprising second image frames from a second camera having a second dynamic range capability; determining a dynamic range of a representation of a scene in the first image frames satisfies first criteria; when the dynamic range satisfies the first criteria, determining output image frames based on a first image frames and the second image frames by processing the first image frames and the second image frames to determine the output image frames having a transition from the first dynamic range capability to the second dynamic range capability. Other aspects and features are also claimed and described.

Abstract: This disclosure provides systems, methods, and devices for image processing. In a first aspect, a method of image processing includes receiving first image data from a first camera of an image capture device, wherein the first camera is different from a second camera of the image capture device; determining a first portion of the first image data; transforming the first portion of the first image data with a first strength based on an alignment difference between the first camera and the second camera; transforming a second portion of the first image data with a second strength based on the alignment difference between the first camera and the second camera; and determining a first output image frame based on the first image data after transforming the first portion of the first image data and transforming the second portion of the first image data. Other aspects and features are also described.

Abstract: This disclosure provides systems, methods, and devices for image processing that support enhanced variable aperture (VA) camera operations. In a first aspect, a method of image processing includes determining first image statistics for first image data representing a first scene captured at a first aperture; and determining whether the first image data satisfies a first criteria. When the first image data satisfies the first criteria, the image processing includes determining an updated lens shading correction (LSC) corresponding to the first aperture based on the first image statistics and on a current LSC corresponding to the first aperture; and determining a first output image frame based on the updated LSC and the first image data. Other aspects and features are also claimed and described.

Abstract: Disclosed are systems, apparatuses, processes, and computer-readable media for processing image data. One illustrative method of processing image data includes: capturing a first image of a subject using a variable aperture lens configured with a first aperture and a first exposure value; capturing a second image of the subject using the variable aperture lens configured with a second aperture and a second exposure value, wherein the second aperture is smaller than the first aperture and the second exposure value is smaller than the first exposure value; and generating a high dynamic range (HDR) image at least in part by fusing the first image and the second image fusing the first image and the second image.

Abstract: Imaging systems and techniques are described. An imaging system receives image data captured by an image sensor according to one or more image capture settings, for instance according to an aperture size, temperature, lux, lens position, and/or region of interest. The image data includes image pixel data and focus pixel data. The imaging system determines a first focus setting based on phase detection using the focus pixel data. The imaging system determines a focus offset based on use of the one or more image capture settings as inputs to a trained model (e.g., decision tree, random forest, neural network). The imaging system determines a second focus setting at least in part by adjusting the first focus setting according to the focus offset, and causes a focus control mechanism to set a focus parameter to the second focus setting.

Abstract: A multi-point measurement of a scene captured in an image frame may be used to process the image frame, such as by applying white balance corrections to the image frame. In some examples, the image frame may be segmented into portions that are illuminated by different illumination sources. Different portions of the image frame may be white balanced differently based on the color temperature of the illumination source for the corresponding portion. Infrared measurements of multiple points in the scene may be used to determine a characteristic of the illumination source of different portions of the scene. For example, a picture that includes indoor and outdoor portions may be illuminated by at least two illumination sources that produce different infrared measurements values. White balancing may be applied differently to these two portions to correct for color temperature of the different sources.

Abstract: This disclosure provides systems, methods, and devices for image processing that support noise reduction in low-light video sequences. The noise reduction is accomplished through a cascaded set of operations that are configured based on each set of operations location within the cascaded pipeline. The cascade may be implemented as a series of cascaded image post-processing engines (IPEs) within an image signal processor (ISP).

Abstract: This disclosure provides systems, methods, and devices for image signal processing that support adjusting a Bokeh effect in image data. In a first aspect, a method of image processing includes receiving a first user input specifying a first depth of focus. A camera is configured with a first aperture size of a plurality of aperture sizes of the camera that is nearest a second aperture size that corresponds to the first depth of focus. The first aperture size is smaller than the second aperture size. Image data representing a scene is received that is captured with the first aperture size of the camera. First modified image data is determined by applying a first blur kernel to the image data. The first modified image data represents the scene at the depth of focus corresponding to the second aperture size. Other aspects and features are also claimed and described.

Abstract: This disclosure provides systems, methods, and devices for image signal processing that support compensating for a diffraction pattern in an image. The diffraction pattern results from blades of a variable aperture of a camera used to capture the image. In a first aspect, a method of image processing includes receiving, by a processor, first image data; determining, by the processor, a characteristic of the first image data correlated with a color temperature of the first image data; determining, by the processor, a compensation matrix based on whether the characteristic exceeds a predetermined threshold, wherein the compensation matrix comprises correction values for reducing red channel peaks in the first image data; and determining, with the computing device, corrected image data based on the first image data and on the compensation matrix. Other aspects and features are also claimed and described.

Abstract: The present disclosure provides systems, apparatus, methods, and computer-readable media that support improved image signal processing, particularly in low-light or high dynamic range (HDR) scenes. The image processing techniques may include performing two automatic exposure control (AEC) operations, in which a first AEC operation targets obtaining good conditions for autofocus (AF) operation, and a second AEC operation follows the AF operation and targets obtaining good conditions for an image capture. The image processing techniques may also include communication between the AEC operations and AF operations to coordinate the operations by locking and releasing exposure levels and focus positions as part of the image signal processing.

Abstract: A method of camera processing including receiving a first image, determining one or more first automatic white balance (AWB) parameters for the first image, determining one or more second AWB parameters for a region-of-interest (ROI) of the first image, applying the one or more first AWB parameters to one or more of the first image or a second image, and adjusting the ROI of one or more of the first image or the second image based on the one or more second AWB parameters.

Abstract: Systems and techniques are provided for processing one or more images. For instance, aspects include a process that can include determining a first region of interest corresponding to a first object depicted in an image obtained using at least one camera. The first region of interest is associated with at least one element of a multi-point grid associated with a multi-point depth sensing system. The process can include determining a first extended region of interest for the first object. The first extended region of interest is associated with a plurality of elements including the at least one element and one or more additional elements of the multi-point grid. The process can further include, based on the plurality of elements associated with the first extended region of interest, determining representative depth information representing a first distance between the at least one camera and the first object depicted in the image.

Abstract: Techniques and systems are provided for improving one or more image capture operations. In some examples, a system determines, based on data from one or more sensors, a movement of an image capture device associated with a capture of a plurality of image frames. The systems adjust a position of at least one object in each of the plurality of image frames based on the movement of the image capture device. The system determines a motion of the at least one object based on a difference in the adjusted position among the plurality of image frames. The system selects a value for at least one image capture parameter associated with the plurality of image frames based on the motion of the at least one object.

Abstract: This disclosure provides systems, methods, and devices for image capture and image processing that support capture using a variable aperture (VA) camera. In a first aspect, a method of image processing includes determining a plurality of depths for a scene, the plurality of depths corresponding to a plurality of regions of interest; determining an aperture size for a camera based on the plurality of depths; determining a lens position for the camera based on the aperture size and the plurality of depths; and controlling the camera to adjust a variable aperture (VA) of the camera based on the aperture size and to adjust a lens associated with the variable aperture (VA) based on the lens position. Other aspects and features are also claimed and described.

Abstract: Aspects of the present disclosure relate to systems and methods for image focusing for devices including multiple cameras. An example method includes estimating a focus distance associated with an image captured by a first camera, determining, based at least in part on the estimated focus distance, to switch from the first camera to a second camera, switching from the first camera to the second camera, completing a focusing operation using the second camera and presenting an updated image captured by the second camera.

Abstract: Disclosed are systems, apparatuses, processes, and computer-readable media to capture images. A method of processing image data includes determining a first region of interest (ROI) in an image. The first ROI is associated with a first object. The method can include determining one or more image characteristics of the first ROI. The method can further include determining whether to perform an upsampling process on image data in the first ROI based on the one or more image characteristics of the first ROI.

Abstract: This disclosure provides systems, methods, and devices for image capture and image processing that support capture using a variable aperture (VA) camera. In a first aspect, a method of image processing includes determining a plurality of depths for a scene, the plurality of depths corresponding to a plurality of regions of interest; determining an aperture size for a camera based on the plurality of depths; determining a lens position for the camera based on the aperture size and the plurality of depths; and controlling the camera to adjust a variable aperture (VA) of the camera based on the aperture size and to adjust a lens associated with the variable aperture (VA) based on the lens position. Other aspects and features are also claimed and described.

Abstract: The present disclosure provides systems, apparatus, methods, and computer-readable media that support multi-frame depth-of-field (MF-DOF) for deblurring background regions of interest (ROIs), such as background faces, that may be blurred due to a large aperture size or other characteristics of the camera used to capture the image frame. The processing may include the use of two image frames obtained at two different focus points corresponding to the multiple ROIs in the image frame. The corrected image frame may be determined by deblurring one or more ROIs of the first image frame using an AI-based model and/or local gradient information. The MF-DOF may allow selectively increasing a depth-of-field (DOF) of an image to provide focused capture of multiple regions of interest, without causing a reduction in aperture (and subsequently an amount of light available for photography) or background blur that may be desired for photography.

Abstract: This disclosure provides systems, methods, and devices for image capture using an autofocus (AF) algorithm. In a first aspect, a method for autofocus includes receiving first image data of a first scene from a first image sensor of a first camera, the first image data comprising phase shift information; determining a first focal distance for the first scene based on a machine learning algorithm by inputting the phase shift information to the machine learning algorithm; and controlling a focal position of the first camera based on the first focal distance. Other aspects and features are also claimed and described.

Abstract: This disclosure provides systems, methods, and devices for image capture using an autofocus (AF) algorithm. In a first aspect, a method for autofocus includes receiving first image data of a first scene from a first image sensor of a first camera, the first image data comprising phase shift information; determining a first focal distance for the first scene based on a machine learning algorithm by inputting the phase shift information to the machine learning algorithm; and controlling a focal position of the first camera based on the first focal distance. Other aspects and features are also claimed and described.