Abstract: A system can include a memory and a motion vector calculator (MVC) configured to receive a block from the memory, the MVC including an MVC core configured to generate a partial motion vector (MV) for the block, a halo reduction block configured to perform halo reduction on the partial MV, and an MV post-processing block configured to smooth the partial MV and output the smoothed partial MV.

Abstract: A method includes receiving, at a processor, a frame of input image data, generating at least one motion vector field between a first frame of input image data and an adjacent frame of input image data, refining the at least one motion vector field to provide refined motion vectors, temporally filtering a frame of input image data to produce a temporally filtered frame of image data, and generating a frame of interpolated image data using the temporally filtered frame of image data and the refined motion vectors.

Abstract: A method of generating super resolution image data includes receiving original image data of a low resolution at an image processing device, performing motion compensation on the original image data using a current frame of image data and at least one previous frame of image data and at least one future frame of image data as reference frames, generating motion vectors, applying noise reduction to the current frame of image data and the reference frames to produce noise reduced, current frame image data, and generating a current frame of super resolution image data using the noise reduced, current frame image data.

Abstract: A method of developing an image training library includes receiving, at a processor, a set of high resolution image samples at a first resolution, generating a set of low resolution image samples having a second resolution from the set of high resolution images, wherein the second resolution is lower than the first resolution, clustering the low resolution image samples using features in the low resolution images, generating a low resolution dictionary for each cluster, generating sparse coefficients for each sample, and using the sparse coefficients to generate a high resolution dictionary for each cluster.

Abstract: A method of scaling image data, includes receiving image data at a processor in at least two channels, the image data having a first resolution for the a channel and a second, lower resolution for other channels, using known pixel values of the first resolution pixels to generate an interpolation function to be applied to second resolution pixels co-located with a subset of the first resolution pixels, and applying the interpolation function to the second resolution pixels to find the unknown pixel values.

Abstract: A system comprises a phase plane correlation (PPC) processing module configured to receive video data from a video source and generate a motion vector (MV) candidate, and a three-dimensional (3D) recursive processing module configured to receive the MV candidate from the PPC processing module, perform 3D recursive processing on a number of MV candidates including the MV candidate received from the PPC processing module, and select one of the MV candidates based on the 3D recursive processing.

Abstract: A method of converting two-dimensional image data to three-dimensional image data includes dividing the image data into blocks, performing motion estimation on the blocks to produce block-based motion vectors, applying a global motion analysis and a local motion analysis to the block-based motion vectors to generate motion-based depth, applying a global image model and a local image model to the block-based motion vectors to generate image-based depth, and generating a three-dimensional view by fusing the motion-based depth and the image-based depth. Other conversion methods are also included.

Abstract: A method of compensating for match errors while generating a super-resolution image, includes receiving, at a processor, an input image having a first resolution forming a low resolution layer, identifying a patch in a unknown high resolution image layer, identifying a corresponding low resolution patch in the low resolution layer, finding at least one matched patch in a match layer having a resolution lower than the first resolution, identifying at least one copy patch in a copy layer having a resolution lower than the high resolution layer, the copy patch to be copied to the high resolution layer, determining an match error between the at least one matched patch and a corresponding low resolution patch, selecting a matrix to transform the match error to provide compensation for the high resolution patch as match error compensation, and modifying the high resolution patch using the match error compensation.

Abstract: A method of generating super resolution image data includes receiving original image data of a low resolution at an image processing device, performing motion compensation on the original image data using a current frame of image data and at least one previous frame of image data and at least one future frame of image data as reference frames, generating motion vectors, applying noise reduction to the current frame of image data and the reference frames to produce noise reduced, current frame image data, and generating a current frame of super resolution image data using the noise reduced, current frame image data.

Abstract: A method of generating new views for a multi-view display system includes receiving a block-based disparity estimate between left image data and right image data for a frame of image data at a processor, upscaling the block-based disparity estimate to a pixel-based disparity for each pixel in the image date, performing motion vector based disparity interpolation and image interpolation simultaneously to produce left and right side interpolated data, and generating at least one new view using left and right side interpolated data.

Abstract: A method of producing a high resolution image includes generating high resolution image data for a high resolution image using a processor, wherein the high resolution image has a resolution higher than a resolution of an original image, determining image content of the high resolution image data, and selectively adding dither noise to the high resolution image data based upon the image content of the high resolution image data to produce final image data.

Abstract: An apparatus has a neighbor motion vector module arranged to receive motion vector data for blocks that neighbor a current pixel and select a predetermined number of block motion vectors, at least two pixel motion vector modules arranged to receive the block motion vector data and to produce interpolated pixel motion vector data, a weighting module configured to produce a weighting for the interpolated pixel motion vector data from the motion vector modules, and a blending module to blend the interpolated pixel motion vector data according to the weighting and to produce pixel output data for the current pixel.

Abstract: A method of processing video data includes upscaling an input low resolution image to a high resolution image using a processor, detecting monotonicity in a direction normal to an edge in a low resolution neighborhood in the input low resolution image, and correcting pixels in a high resolution neighborhood of the high resolution image corresponding to the low resolution neighborhood to preserve at least some of the monotonicity.

Abstract: A method of determining an output frame rate includes receiving an input sequence of frames of image data at an input frame rate, performing motion vector calculations on the frames of image data to produce motion vectors and motion statistics, determining a motion level in the frames using the motion statistics, and interpolating frames of image data at the output frame rate, wherein the output frame rate is based upon the motion level.

Abstract: A method of generating motion vectors for image data includes identifying boundaries of at least one object in original frames of image data, performing object motion analysis based upon the boundaries, performing pixel-level motion layer generation, using the object motion analysis and the pixel-level motion layers to generate motion for blocks in the image data, and producing block level motion information and layer information for the original frames of image data.

Abstract: An apparatus includes a display device having a pixel and vector storage, and a by-pass mode and an interpolation mode, wherein the interpolation mode converts input data from an input frame rate to a display refresh rate based on pixel and vector data stored in the storage. A method includes determining a selected interpolation mode to be employed by a frame interpolator, retrieving pixel data and vector data received from a host system from a storage, and generating interpolated frames of display data according to the selected interpolation mode.

Abstract: An on-screen display (OSD) processing system can include video data fetch modules to receive video data from a video source, edge detection modules to detect an edge of a region within a scene represented by the video data, edge processing modules to process results from the edge detection modules, and an OSD confidence level adjustment module to adjust an OSD confidence level corresponding to the region within the scene.

Abstract: A method and system for detecting and processing a series of video frames includes receiving the series of video frames, determining whether the video frames are associated with a recognized non-video source, and depending on the determination, processing the video frames using a variety of techniques. A system may detect whether each video frame is a repeat frame or a new original frame, keep the new original frames, discard the repeat frames, and then adjust one or more timestamps associated with the new original frames so as to conform to an intermediate frame rate. The frame indexes and timestamps associated with the new original frames are stored in a FIFO or buffer. The system can interpolate video frames using the stored timestamps, and output a series of video frames. The output video stream is delivered at any frame rate and can include original video frames and interpolated video frames.

Abstract: A method of generating a super-resolution image from a single frame of image data includes using a processor to retrieve query patches of image data from a memory, determining a search range for each patch, and generating super-resolution image data corresponding to each patch based upon the search range.

Abstract: To denoise video data, a temporal IIR filter is applied to video data. The temporally filtered frame is used as a guide to spatially filter the video data without introducing temporal artifacts. The spatially filtered frame can then be temporally filtered again using a temporal IIR filter. The results of the second temporal filtering can then be used as a guide to eliminate noise that the spatial filter did not eliminate.