Abstract: According to an embodiment of the disclosure, the method may include obtaining an image of a scene including an object of interest to be tracked in at least one camera mode, obtaining image data of at least two consecutive frames in the at least one camera mode based on the image, estimating a disparity and a reliability of the scene including the object of interest based on the image data, estimating a camera-to-object distance based on the disparity and the reliability, switching the camera mode based on the camera-to-object distance.

Abstract: A device for gathering image sets includes: N digital cameras including one or more ground truth cameras for capturing high quality ground truth images and one or more target cameras for capturing low quality target images, the N digital cameras being optically coupled via N?1 beam splitters, at least N?1 cameras of the N digital cameras being mounted on automatically adjustable mounts; and at least one computer readable storage device storing instructions executable by at least one processor. The instructions cause the at least one processor to adjust the at least N?1 cameras by actuating the automatically adjustable mounts on which the at least N?1 cameras are mounted; synchronize image capture by the digital cameras; and control the digital cameras to gather sets of N images. The at least N?1 cameras are adjusted based on at least one set of N images of the scene.

Abstract: A method and device for predictive autofocus on an object are provided.

Abstract: A device for gathering image sets includes: N digital cameras including one or more ground truth cameras for capturing high quality ground truth images and one or more target cameras for capturing low quality target images, the N digital cameras being optically coupled via N?1 beam splitters, at least N?1 cameras of the N digital cameras being mounted on automatically adjustable mounts; and at least one computer readable storage device storing instructions executable by at least one processor. The instructions cause the at least one processor to adjust the at least N?1 cameras by actuating the automatically adjustable mounts on which the at least N?1 cameras are mounted; synchronize image capture by the digital cameras; and control the digital cameras to gather sets of N images. The at least N?1 cameras are adjusted based on at least one set of N images of the scene.

Abstract: A method for converting a frame rate of an input video is provided. The method includes performing a motion estimation by generating at least one motion field for at least one pair of frames of the input video, wherein the at least one motion field includes a set of motion vectors for each block of a first reference frame of the input video, the set of motion vectors indicating to a second reference frame of the input video, and preparing first data for a predetermined interpolation phase for each block of an interpolated frame, where the first data include at least one parameter for a pre-trained occlusion processing (OcC) convolutional neural network (CNN), the at least one parameter being obtained based on the at least one motion field.

Abstract: A video frame rate conversion (FRC) method, including obtaining at least one pair of frames of a video; partitioning each frame into a plurality of blocks; estimating motion a block-by-block basis to obtain: a forward motion field including a set of first motion vectors, and a backward motion field including a set of second motion vectors; obtaining occlusions based on the forward motion field and the backward motion field; and calculating an artifact probability metric indicating a probability of an appearance of an artifact in the motion-compensated frame interpolation between the first frame and the second frame.

Abstract: A method and device for predictive autofocus on an object are provided.

Abstract: A method for converting a frame rate of an input video is provided. The method includes performing a motion estimation by generating at least one motion field for at least one pair of frames of the input video, wherein the at least one motion field includes a set of motion vectors for each block of a first reference frame of the input video, the set of motion vectors indicating to a second reference frame of the input video, and preparing first data for a predetermined interpolation phase for each block of an interpolated frame, where the first data include at least one parameter for a pre-trained occlusion processing (OcC) convolutional neural network (CNN), the at least one parameter being obtained based on the at least one motion field.

Abstract: A motion estimation method for video data including frames and an apparatus therefor are provided. The motion estimation method includes determining whether a current frame unit for which motion estimation is to be performed corresponds to a double block, when the current frame unit corresponds to a double block, acquiring a candidate vector set corresponding to a first single block included in the double block, as a candidate vector set of the double block, individually calculating a confidence function value of each candidate vector included in the candidate vector set of the double block, for the first single block and a second single block included in the double block, and acquiring an estimated motion vector of the first single block and an estimated motion vector of the second single block, based on the calculated confidence function value of each candidate vector.

Abstract: A motion estimation method for video data including frames and an apparatus therefor are provided. The motion estimation method includes determining whether a current frame unit for which motion estimation is to be performed corresponds to a double block, when the current frame unit corresponds to a double block, acquiring a candidate vector set corresponding to a first single block included in the double block, as a candidate vector set of the double block, individually calculating a confidence function value of each candidate vector included in the candidate vector set of the double block, for the first single block and a second single block included in the double block, and acquiring an estimated motion vector of the first single block and an estimated motion vector of the second single block, based on the calculated confidence function value of each candidate vector.