Abstract: A method for creating a composite image provides for determining, based on orientation sensor data sampled in association with each frame in an image sequence, camera orientation information indicating an orientation of the camera at a time that the frame was captured. Based at least in part on the orientation sensor data, a subset of orientationally-similar frames from the sequence fare identified and combined together to create the composite image.

Abstract: Methods, systems, apparatuses, and computer-readable storage mediums described herein are configured to fuse image frames captured by a camera to generate an image frame having high dynamic range and reduced amount of noise. For instance, after a shutter button of the camera is activated, one or more history image frames captured during a preview mode of the camera (e.g., before the shutter button is activated) are compared to a highlight recovery frame captured after the shutter button is activated to determine a level of similarity therebetween. The history image frame(s) may be captured with a first exposure value, and the highlight recovery frame may be captured with a second exposure value that is different than the first exposure value. History image frame(s) that are determined to be relatively similar to the highlight recovery frame are combined with the highlight recovery frame to generate the image frame having high dynamic range.

Abstract: Methods, systems, apparatuses, and computer-readable storage mediums described herein are configured to fuse image frames captured by a camera to generate an image frame having high dynamic range and reduced amount of noise. For instance, after a shutter button of the camera is activated, one or more history image frames captured during a preview mode of the camera (e.g., before the shutter button is activated) are compared to a highlight recovery frame captured after the shutter button is activated to determine a level of similarity therebetween. The history image frame(s) may be captured with a first exposure value, and the highlight recovery frame may be captured with a second exposure value that is different than the first exposure value. History image frame(s) that are determined to be relatively similar to the highlight recovery frame are combined with the highlight recovery frame to generate the image frame having high dynamic range.

Abstract: Methods, systems, apparatuses, and computer-readable storage mediums described herein are configured to fuse image frames captured by a camera to generate an image frame having high dynamic range and reduced amount of noise. For instance, after a shutter button of the camera is activated, one or more history image frames captured during a preview mode of the camera (e.g., before the shutter button is activated) are compared to a highlight recovery frame captured after the shutter button is activated to determine a level of similarity therebetween. The history image frame(s) may be captured with a first exposure value, and the highlight recovery frame may be captured with a second exposure value that is different than the first exposure value. History image frame(s) that are determined to be relatively similar to the highlight recovery frame are combined with the highlight recovery frame to generate the image frame having high dynamic range.

Abstract: An optical image stabilization (OIS) system is configured to generate a still image from image frames captured during a video capture mode to provide efficient multiframe image enhancement. The OIS is configured in response to detection of a request to generate a still image during capture of a plurality of image frames of a scene by a device (such as during video capture). The configured OIS maintains a field-of-view of the scene over the subsequent, successive image frames, which are captured and used to generate the still image with less processing resources, less memory and/or less battery power.

Abstract: A computer-implemented flash artifact removal apparatus is described. The apparatus has at least a memory storing a flash image depicting a person's face captured in the presence of a flash illumination, and a non-flash image depicting the person's face captured without flash illumination. A plurality of pixels in the flash image comprise artifacts as a result of flash light reflecting from one or more eyes of the person. The apparatus has a flash artifact removal component which corrects the flash image by replacing at least some of the plurality of pixels in the flash image with pixels computed from at least the non-flash image. The flash artifact removal component is configured to detect edges of features of the one or more eyes in the non-flash image and to detect the plurality of pixels to be replaced in the flash image on the basis of the detected edges.

Abstract: An optical image stabilization (OIS) system is configured to generate a still image from image frames captured during a video capture mode to provide efficient multiframe image enhancement. The OIS is configured in response to detection of a request to generate a still image during capture of a plurality of image frames of a scene by a device (such as during video capture). The configured OIS maintains a field-of-view of the scene over the subsequent, successive image frames, which are captured and used to generate the still image with less processing resources, less memory and/or less battery power.

Abstract: A computer-implemented flash artifact removal apparatus is described. The apparatus has at least a memory storing a flash image depicting a person's face captured in the presence of a flash illumination, and a non-flash image depicting the person's face captured without flash illumination. A plurality of pixels in the flash image comprise artifacts as a result of flash light reflecting from one or more eyes of the person. The apparatus has a flash artifact removal component which corrects the flash image by replacing at least some of the plurality of pixels in the flash image with pixels computed from at least the non-flash image. The flash artifact removal component is configured to detect edges of features of the one or more eyes in the non-flash image and to detect the plurality of pixels to be replaced in the flash image on the basis of the detected edges.