Abstract: Techniques are described for automated analysis and filtering of image data. Image data is analyzed to identify regions of interest (ROIs) within the image content. The image data also may have depth estimates applied to content therein. One or more of the ROIs may be designated to possess a base depth, representing a depth of image content against which depths of other content may be compared. Moreover, the depth of the image content within a spatial area of an ROI may be set to be a consistent value, regardless of depth estimates that may have been assigned from other sources. Thereafter, other elements of image content may be assigned content adjustment values in gradients based on their relative depth in image content as compared to the base depth and, optionally, based on their spatial distance from the designated ROI. Image content may be adjusted based on the content adjustment values.

Abstract: Techniques are disclosed for capturing stereoscopic images using one or more high color density or “full color” image sensors and one or more low color density or “sparse color” image sensors. Low color density image sensors, may include substantially fewer color pixels than the sensor's total number of pixels, as well as fewer color pixels than the total number of color pixels on the full color image sensor. More particularly, the mostly-monochrome image captured by the low color density image sensor may be used to reduce noise and increase the spatial resolution of an imaging system's output image. In addition, the color pixels present in the low color density image sensor may be used to identify and fill in color pixel values, e.g., for regions occluded in the image captured using the full color image sensor. Optical Image Stabilization and/or split photodiodes may be employed on one or more sensors.

Abstract: Techniques are disclosed for capturing stereoscopic images using one or more high color density or “full color” image sensors and one or more low color density or “sparse color” image sensors. Low color density image sensors, may include substantially fewer color pixels than the sensor's total number of pixels, as well as fewer color pixels than the total number of color pixels on the full color image sensor. More particularly, the mostly-monochrome image captured by the low color density image sensor may be used to reduce noise and increase the spatial resolution of an imaging system's output image. In addition, the color pixels present in the low color density image sensor may be used to identify and fill in color pixel values, e.g., for regions occluded in the image captured using the full color image sensor. Optical Image Stabilization and/or split photodiodes may be employed on one or more sensors.

Abstract: Techniques are described for automated analysis and filtering of image data. Image data is analyzed to identify regions of interest (ROIs) within the image content. The image data also may have depth estimates applied to content therein. One or more of the ROIs may be designated to possess a base depth, representing a depth of image content against which depths of other content may be compared. Moreover, the depth of the image content within a spatial area of an ROI may be set to be a consistent value, regardless of depth estimates that may have been assigned from other sources. Thereafter, other elements of image content may be assigned content adjustment values in gradients based on their relative depth in image content as compared to the base depth and, optionally, based on their spatial distance from the designated ROI. Image content may be adjusted based on the content adjustment values.