Abstract: An image frame interpolation apparatus includes a motion vector generator configured to generate a motion vector based on a first image frame and a second image frame; a motion scaler configured to scale the motion vector to thereby generate a scaled motion vector; and a motion compensator including an internal memory, the motion compensator being configured to perform motion compensation based on the scaled motion vector and generate an interpolation frame using the internal memory, the motion scaler being configured to scale the motion vector based on a size of the motion vector and a size of the internal memory.

Abstract: An electronic apparatus is provided. The electronic apparatus includes: a storage configured to store a plurality of filters each corresponding to a plurality of image patterns; and a processor configured to classify an image block including a target pixel and a plurality of surrounding pixels into one of the plurality of image patterns based on a relationship between pixels within the image block and to obtain a final image block in which the target pixel is image-processed by applying at least one filter corresponding to the classified image pattern from among the plurality of filters to the image block, wherein the plurality of filters are obtained by learning, through an artificial intelligence algorithm, a relationship between a plurality of first sample image blocks and a plurality of second sample image blocks corresponding to the plurality of first sample image blocks based on each of the plurality of image patterns.

Abstract: A motion vector estimation method of a motion vector estimation apparatus are provided. The motion vector estimation method of the motion vector estimation apparatus includes: determining a motion vector of a current block by setting, in another frame, a local search area for searching a plurality of reference pixel blocks corresponding to the current block which is one of pixel blocks in a single frame; and finally determining one of the determined motion vector and a previous motion vector referred to in order to determine the local search area as a motion vector of the current block, based on sum of absolution difference (SAD) values of the reference pixel blocks included in the local search area.

Abstract: A display apparatus is provided. The display apparatus includes an input interface, a first storage, a display, and a processor. Pixel values corresponding to a predetermined number of lines in an image input through the input interface are stored in the first storage. The processor acquires a first patch of a predetermined size by sampling a number of pixel values located in an outer region of a matrix centering about a specific pixel value from among the pixel values stored in the first storage, acquires a high-frequency component for the specific pixel value based on the acquired first patch, and processes the input image based on the high-frequency component. The display displays the processed image.

Abstract: A display apparatus is provided. The display apparatus according to an exemplary embodiment includes a display, and a processor configured to generate a second image and a third image where a dynamic range is expanded by respectively applying a first gain and a second gain to an input first image, generate a degraded image of the second image by applying a predetermined degradation model to the second image, based on a difference value between a pixel of the degraded second image and a pixel of the third image satisfying a predetermined condition, modify a pixel value of the second image based on the difference value, and output the second image where the pixel value is modified through the display.

Abstract: A frame rate conversion apparatus is provided. The frame rate conversion apparatus includes at least one processor configured to determine a noise strength of a block of a current frame among a plurality of frames forming an input video, generate a block of an interpolation frame corresponding to the block of the current frame by estimating a motion vector of a block of the interpolation frame based on the noise strength, and insert the interpolation frame between the current frame and an adjacent frame to adjust a frame rate of the input video.

Abstract: A display apparatus and a method of processing an image thereof are provided. The method includes identifying at least one area of an input image by analyzing a dynamic range of the input image, obtaining at least one mapping function based on dynamic range information and brightness information of the at least one area and dynamic range information of the display apparatus, obtaining at least one virtual image where the dynamic range of the input image is converted using the at least one mapping function, synthesizing the at least one virtual image and the input image, and outputting the synthesized image.

Abstract: An image processing apparatus includes: a signal receiver configured to receive an input image; an image processor configured to process the input image and generate an output image; a storage configured to store a first patch corresponding to a first pixel of the input image; and a controller configured to control the image processor to generate the output image by applying the first patch stored in the storage to the first pixel.

Abstract: Disclosed is a motion vector smoothing method. The motion vector smoothing method includes acquiring motion vectors of at least one block of a current image by using a reference image, acquiring a candidate motion vector of a current block, based on a motion vector of the current block, and at least one motion vector of at least one block adjacent to the current block, determining a threshold value of the current block according to gradient values of pixels included in the current block, and determining the motion vector of the current block according to the threshold value.

Abstract: A video processing method includes generating a first down-sampled block by down-sampling a first block included in a first frame; generating a plurality of second down-sampled blocks by down-sampling a second block included in a second frame; selecting one of the plurality of second down-sampled blocks by comparing the first down-sampled block and each of the plurality of second down-sampled blocks; and determining, based on the first down-sampled block and the one selected second down-sampled block, a motion vector whereby the second block points to the first block, wherein the plurality of second down-sampled blocks are generated using down-sampling methods that are different from each other with respect to samples of the second block.

Abstract: A frame rate conversion apparatus is provided. The frame rate conversion apparatus includes at least one processor configured to determine a noise strength of a block of a current frame among a plurality of frames forming an input video, generate a block of an interpolation frame corresponding to the block of the current frame by estimating a motion vector of a block of the interpolation frame based on the noise strength, and insert the interpolation frame between the current frame and an adjacent frame to adjust a frame rate of the input video.

Abstract: A motion vector estimation method of a motion vector estimation apparatus are provided. The motion vector estimation method of the motion vector estimation apparatus includes: determining a motion vector of a current block by setting, in another frame, a local search area for searching a plurality of reference pixel blocks corresponding to the current block which is one of pixel blocks in a single frame; and finally determining one of the determined motion vector and a previous motion vector referred to in order to determine the local search area as a motion vector of the current block, based on sum of absolution difference (SAD) values of the reference pixel blocks included in the local search area.

Abstract: The present invention relates to a method and apparatus for motion estimation (ME) of a video in a video system. The method includes estimating an occlusion area by using a pattern map; removing a motion vector which corresponds to the estimated occlusion area from a motion vector field, and outputting remaining motion vectors as first candidate motion vectors; collecting motion vectors which correspond to an area of interest in the input video, detecting a representative motion vector which represents the collected motion vectors, and comparing the first candidate motion vectors with the representative motion vector removing a first candidate motion vector having a difference in a weight value from the representative motion vector which is greater than a first threshold value and outputting the remaining first candidate motion vectors as second candidate motion vectors; and performing a motion estimation operation by using the second candidate motion vectors.

Abstract: A hierarchical motion prediction apparatus and method. The hierarchical motion prediction method splits a current frame and a reference frame into pixel groups, changes a pixel location of each pixel group, and selects one pixel, and thus resolutions of the current frame and reference frame are reduced. A motion vector of a down-sampled current block is obtained based on a down-sampled current frame and reference frame, and is expanded to a motion vector of an original resolution based on a down sampling rate.

Abstract: A hierarchical motion prediction apparatus and method. The hierarchical motion prediction method splits a current frame and a reference frame into pixel groups, changes a pixel location of each pixel group, and selects one pixel, and thus resolutions of the current frame and reference frame are reduced. A motion vector of a down-sampled current block is obtained based on a down-sampled current frame and reference frame, and is expanded to a motion vector of an original resolution based on a down sampling rate.

Abstract: A method and apparatus for encoding an image, and a method and apparatus for decoding an image. The method of encoding an image includes: classifying pixels forming an input image into a first pixel group in which bit depth of original pixel values is maintained, and a second pixel group in which bit depth of original pixel values is changed; generating a changed input image by changing the bit depth of pixel values of pixels in the second pixel group; and performing motion prediction and compensation on the changed input image.

Abstract: A method for processing image data corresponding to temporally successive motions of an object, the method including adjusting a range of a first occlusion region which is estimated according to whether position changes occur in sub-blocks forming temporally successive first and second frames among image frames which display the motions of the object, by using Motion Vectors (MVs) mapped to the sub-blocks and detecting a second occlusion region of a third frame which displays the object that moves between the first frame and the second frame, by using the adjusted range of the first occlusion region.

Abstract: An image frame interpolation apparatus includes a motion vector generator configured to generate a motion vector based on a first image frame and a second image frame; a motion scaler configured to scale the motion vector to thereby generate a scaled motion vector; and a motion compensator including an internal memory, the motion compensator being configured to perform motion compensation based on the scaled motion vector and generate an interpolation frame using the internal memory, the motion scaler being configured to scale the motion vector based on a size of the motion vector and a size of the internal memory.

Abstract: Disclosed is a motion vector smoothing method. The motion vector smoothing method includes acquiring motion vectors of at least one block of a current image by using a reference image, acquiring a candidate motion vector of a current block, based on a motion vector of the current block, and at least one motion vector of at least one block adjacent to the current block, determining a threshold value of the current block according to gradient values of pixels included in the current block, and determining the motion vector of the current block according to the threshold value.

Abstract: A method and apparatus for generating an interpolated frame are provided. The method includes: generating a motion vector for generating a third frame by performing motion estimation based on first image data and second image data, the first image data being a portion of image data of a first frame and the second image data being a portion of image data of a second frame; restoring the image data of the first frame based on the first image data and the image data of the second frame based on the second image data; and generating the third frame by performing motion compensation based on at least one of the restored image data of the first frame and the restored image data of the second frame and the generated motion vector.