Methods, systems, computer-readable media, and apparatuses for image processing and utilization are presented. In some embodiments, an image containing at a face of a user may be obtained using a mobile device. An orientation of the face of the user within the image may be determined using the mobile device. The orientation of the face of the user may be determined using multiple stages: (a) a rotation stage for controlling a rotation applied to a portion of the image, to generate a portion of rotated image, and (b) an orientation stage for controlling an orientation applied to orientation-specific feature detection performed on the portion of rotated image. The determined orientation of the face of the user may be utilized as a control input to modify a display rotation of the mobile device.

An image signal processor for generating a converted image based on a raw image includes processing circuitry configured to store data corresponding to a plurality of lines of a received image in a line buffer, perform an image processing operation by filtering the data stored in the line buffer based on at least one filter, and divide the raw image into a plurality of sub-images and request the plurality of sub-images from a memory in which the raw image is stored, such that the plurality of sub-images are sequentially received by the line buffer, a width of each of the plurality of sub-images being less than a width of the line buffer, and the plurality of sub-images being parallel to each other.

An image signal processor for generating a converted image based on a raw image includes processing circuitry configured to store data corresponding to a plurality of lines of a received image in a line buffer, perform an image processing operation by filtering the data stored in the line buffer based on at least one filter, and divide the raw image into a plurality of sub-images and request the plurality of sub-images from a memory in which the raw image is stored, such that the plurality of sub-images are sequentially received by the line buffer, a width of each of the plurality of sub-images being less than a width of the line buffer, and the plurality of sub-images being parallel to each other.

An image processing system includes: an image processing device that comprises a first display and a first hardware processor; and an information processing device that communicates with the image processing device, and comprises: a second display on which a second screen same as a first screen being displayed on the first display is displayed; and a second hardware processor, wherein one of the first and second hardware processors determines whether a screen display standard of the first display is left or right standard and whether a screen display standard of the second display is left or right standard, and inverts the second screen that is same as the first screen being displayed on the first display and is displayed on the second display right and left, when the screen display standards of the first and second displays are determined to be different from each other.

A reproducing device that can reproduce data and operates on a battery includes displaying means, attitude detecting means for detecting an attitude of the reproducing device, determining means for determining whether the reproducing device satisfies a predetermined condition, and controlling means for changing a setting of the reproducing device on a basis of a result of detection of the attitude detecting means when the determining means determines that the reproducing device satisfies the predetermined condition.

Methods, system, and computer storage media are provided for novel view synthesis. An input image depicting an object is received and utilized to generate, via a neural network, a target view image. In exemplary aspects, additional view images are also generated within the same pass of the neural network. A loss is determined based on the target view image and additional view images and is used to modify the neural network to reduce errors. In some aspects, a rotated view image is generated by warping a ground truth image from an initial angle to a rotated view angle that matches a view angle of an image synthesized via the neural network, such as a target view image. The rotated view image and the synthesized image matching the rotated view angle (e.g., a target view image) are utilized to compute a rotational loss.

Methods, system, and computer storage media are provided for novel view synthesis. An input image depicting an object is received and utilized to generate, via a neural network, a target view image. In exemplary aspects, additional view images are also generated within the same pass of the neural network. A loss is determined based on the target view image and additional view images and is used to modify the neural network to reduce errors. In some aspects, a rotated view image is generated by warping a ground truth image from an initial angle to a rotated view angle that matches a view angle of an image synthesized via the neural network, such as a target view image. The rotated view image and the synthesized image matching the rotated view angle (e.g., a target view image) are utilized to compute a rotational loss.

A method for rotating a digital image in order to print a corresponding rotated print image. The method includes i) providing the digital image to be printed on the printing substrate; ii) receiving positioning coordinates of the substrate relative to a first predefined reference; and iii) rotating the image relative to its centre as a function of the positioning coordinates, thus determining a rotated image. According to one aspect, the rotation is performed by means of a technique of mapping between pixels of the rotated image and pixels of the digital image, and calculating a matrix of correspondences between the pixels of the rotated image and the pixels of the digital image. According to another aspect, the matrix is configured to indicate how many pixels of the rotated image correspond to pixels of the digital image.

A method, system, and computer program product provide the ability to ink a drawing. A coarse original sketch is loaded. User input drawing an initial stroke over the coarse original sketch is accepted. A stroke smoothness of the initial stroke is measured. A similarity between the initial stroke and the coarse original sketch is measured to determine a snap affect. The stroke smoothness and the snap affect are combined. The initial stroke is automatically/dynamically, without additional user input, modified based on the combination.

Systems, methods, and media for adjusting one or more images displayed to a viewer are provided. In some implementations, the system comprises: at least one processing circuit configured to: detect an orientation of a viewer based on at least two points associated with the viewer; determine, based on the orientation, a rotational position of a first image to be displayed on a display; and generate a display image for display on the display, wherein the display image includes at least a portion of the first image rotated based on the rotational position.