Abstract: A method for training data generation includes obtaining a first set of image frames of a scene and a second set of image frames of the scene using multiple exposure settings. The method also includes generating an alignment map, a blending map, and an input image using the first set of image frames. The method further includes generating a ground truth image using the alignment map, the blending map, and the second set of image frames. In addition, the method includes using the ground truth image and the input image as an image pair in a training dataset when training a machine learning model to reduce image distortion and noise.

Abstract: A method includes obtaining, using a stationary sensor of an electronic device, multiple image frames including first and second image frames. The method also includes generating, using multiple previously generated motion vectors, a first motion-distorted image frame using the first image frame and a second motion-distorted image frame using the second image frame. The method further includes adding noise to the motion-distorted image frames to generate first and second noisy motion-distorted image frames. The method also includes performing (i) a first multi-frame processing (MFP) operation to generate a ground truth image using the motion-distorted image frames and (ii) a second MFP operation to generate an input image using the noisy motion-distorted image frames.

Abstract: A method to record or reproduce a moving picture includes generating main video streams when a moving picture is photographed, lowering a resolution of the main video streams so as to generate sub video streams, multiplexing the main video streams and the sub video streams so as to generate one file, and storing the generated file. Since only the sub video streams obtained by lowering the resolution of I-frames are displayed on the display unit, a picture decoding time is shortened and a picture may be rapidly and easily browsed and edited.

Abstract: A digital imaging apparatus for creating a panorama image and a method thereof, wherein the digital imaging apparatus comprises a capture part for consecutively capturing a plurality of images, an image information detection part for detecting image information regarding the plurality of images output from the capture part, respectively, and a panorama image generation part for converting the plurality of images based on the image conversion information. The image conversion information is determined by selecting one set of the plurality of image information output from the image information detection part, converting the image information regarding the plurality of images output from the capture part using the selected image information, and combining the converted images, thereby creating a natural-looking panorama image.

Abstract: A digital imaging apparatus for creating a panorama image and a method thereof, wherein the digital imaging apparatus comprises a capture part for consecutively capturing a plurality of images, an image information detection part for detecting image information regarding the plurality of images output from the capture part, respectively, and a panorama image generation part for converting the plurality of images based on the image conversion information. The image conversion information is determined by selecting one set of the plurality of image information output from the image information detection part, converting the image information regarding the plurality of images output from the capture part using the selected image information, and combining the converted images, thereby creating a natural-looking panorama image.