Abstract: A depth estimation and conversion apparatus and method is provided. Depth of an video may be estimated by extracting feature information from the input video, and estimating the depth of the input video based on the extracted feature information.

Abstract: A bit-resolution-extension method is provided. The resolution extension method includes normalizing n-m upper bit values of adjacent pixels based on an upper n-m bit value of each pixel of a sample image, analyzing a statistical distribution of a lower m bit value of the reference pixel by patterns of a set consisting of the normalized adjacent pixels, generating a memory address from normalized adjacent pixel values of the sample image, saving a representative value of the lower m bits by patterns to the memory address as a result of the analysis, normalizing adjacent pixel values based on each pixel value of an input image, generating the memory address from the normalized adjacent pixel value of the input image, reading a representative value of the lower m bits saved in the memory address, and adding the read lower m bits to the input image pixel values as lower bits.

Abstract: An apparatus and method of up-converting a frame rate using frames that are decoded from a video decoder and motion information, the apparatus including: a motion vector resampling unit to resample a motion vector for the interpolated frame by filtering a motion vector of a current block using the motion vector of the current block and motion vectors of adjacent blocks in the decoded frame; a motion compensating unit to compensate a motion of the decoded frame by the resampled motion vector to produce the interpolated frame; and a switch to selectively output one of the decoded frame and the interpolated frame according to the sequential order of the frames.

Abstract: An image processing method and apparatus may generate a reference layer about a reference viewpoint. The reference layer may include information used to perform a hole recovery with respect to holes within output images. The information may be generated by warping the reference layer to a viewpoint of an output image.

Abstract: A three-dimensional (3D) image generator and 3D image generation method scale a depth map or a two-dimensional (2D) image, perform a cross filtering to sharpen a blurred region on the depth map based on location information of the depth map and 2D image, and thus obtain a clearer depth map and provide a more graphical 3D image using the depth map.

Abstract: An apparatus and method estimate disparities of pixels in a frame. In order to acquire temporally-consistent disparity maps it is determined whether to enforce a temporal consistency with respect to pixels. In order to determine whether to enforce the temporal consistency, a texture, motion, or a matched motion in the frame may be detected or estimated. A disparity of a pixel where the temporal consistency is enforced may be calculated based on a disparity of a corresponding pixel in a previous frame.

Abstract: A disparity estimation system, apparatus, and method of estimating a consistent depth from a multi-view video. When estimating a disparity at a plurality of viewpoints, the disparity estimation system may estimate a temporally consistent disparity considering a temporal smoothness between proximate frames.

Abstract: Provided is a method, computer-readable medium apparatus that may estimate a disparity of three view images. A global matching may be performed to calculate a global path by performing a dynamic programming on the three view images, and a local matching for supplementing an occlusion region of the calculated global path may be performed, and thereby a disparity estimation of the three view images may be performed.

Abstract: Disclosed is an image conversion device and method converting a two-dimensional (2D) image into a three-dimensional (3D) image. The image conversion device may selectively adjust illumination within the 2D image, generate a disparity map for the illumination adjusted image, and selectively adjust a depth value of the disparity map based on edge discrimination.

Abstract: A local multi-view image display apparatus and method is provided. The local multi-view image display method may track a location of an observer, and locally display a multi-view input image on the tracked location.

Abstract: A method, apparatus, and medium of converting a two-dimensional (2D) image to a three-dimensional (3D) image based on visual attention are provided. A visual attention map including visual attention information, which is information about a significance of an object in a 2D image, may be generated. Parallax information including information about a left eye image and a right eye image of the 2D image may be generated based on the visual attention map. A 3D image may be generated using the parallax information.

Abstract: A depth estimation and conversion apparatus and method is provided. Depth of an video may be estimated by extracting feature information from the input video, and estimating the depth of the input video based on the extracted feature information.

Abstract: A bit resolution-extension method is provided. The bit resolution-extension method includes acquiring the shortest distance from a central pixel to a positive contour and the shortest distance from the central pixel to a negative contour in a filtering region which scans the positive contour comprising large pixels of a fixed value and the negative contour comprising small pixels of a fixed value, based on a value of the central pixel, generating an extension bit of the central pixel by interpolating the shortest distance from the central pixel to the positive contour and the shortest distance from the central pixel to the negative contour, and adding the extension bit as a lower bit of the central pixel.

Abstract: A depth estimation apparatus is provided. The depth estimation apparatus may estimate a depth value of at least one pixel composing an input video based on feature information about at least one feature of the input video, a position of the at least one pixel, and a depth relationship among the at least one pixel and neighboring pixels.

Abstract: A three-dimensional (3D) image generator and 3D image generation method scale a depth map or a two-dimensional (2D) image, perform a cross filtering to sharpen a blurred region on the depth map based on location information of the depth map and 2D image, and thus obtain a clearer depth map and provide a more graphical 3D image using the depth map.

Abstract: A conversion method and apparatus with a generating of a depth map for two dimensional (2D)-to-three dimensional (3D) conversion. A depth order may be restored based on a line tracing and an edge map generated from an input image, and a stereo image may be generated using depth information.

Abstract: A method and apparatus for expanding bit resolution using local information of an image receives an input image. First, second and third threshold value used to enhance bit resolution, to detect a texture and to detect a pattern, respectively, are determined considering global information of the input image. A texture existing in a mask region composed of surrounding pixels within a predetermined range around a current pixel is determined using the second threshold value. A regularly repeated pattern existing in the mask region is determined using the third threshold value if no texture exists in the mask region. The first threshold value is decreased if a texture or pattern exists in the mask region. Values of mask region pixels are adjusted depending on the first threshold value, and bit resolution of the current pixel value is enhanced using a resultant value obtained by filtering the adjusted pixel values.

Abstract: Disclosed are a digital television video program providing system, a digital television, and a control method for the same. The digital television video program providing system includes a video analyzing unit for extracting search terms from information data associated with a played video, a search keyword extracting unit for selecting a search keyword from the extracted search terms based on a reliability factor acquired by an extraction method of the extracted search terms, a video search unit for searching for a playable video based on the selected search keyword, and a search result providing unit for providing search results for the video.

Abstract: An apparatus and method of up-converting a frame rate using frames that are decoded from a video decoder and motion information, the apparatus including: a motion vector resampling unit to resample a motion vector for the interpolated frame by filtering a motion vector of a current block using the motion vector of the current block and motion vectors of adjacent blocks in the decoded frame; a motion compensating unit to compensate a motion of the decoded frame by the resampled motion vector to produce the interpolated frame; and a switch to selectively outputt one of the decoded frame and the interpolated frame according to the sequential order of the frames.

Abstract: Provided is a method and apparatus for compensating for a misalignment of an optical modulator. The method includes performing gamma correction on an input signal having M gradation levels and outputting a preprocessed signal; performing a linearization transform on the preprocessed signal, performing a uniformity transform on the linearly transformed signal to limit a region of the linearly transformed signal, and outputting a compensated signal; and receiving the output compensated signal using the optical modulator and outputting a compensated luminance value.