Abstract: The present disclosure relates to encoding and decoding video by employing texture coding. In particular, a texture region is identified within a video picture and a texture patch is determined for the texture region. Moreover, a first set of parameters is derived specifying weighting factors for reconstructing spectral coefficients of the texture region by fitting the texture region in a spectral domain to a first function of the texture patch, the first function being defined by the first set of parameters. The texture patch and the first set of parameters are then included into a bitstream which is output by an encoder and provided in this way to the decoder which reconstructs the texture based on the patch and the function applied to the patch.

Abstract: The present disclosure relates to encoding a decoding video employing texture coding. In particular, a texture region is identified within a video picture and a texture patch is determined for said region. Moreover, a set of parameters specifies luminance within the texture region (1001) by fitting the texture region samples to a two-dimensional polynomial function of the patch determined according to the set of parameters (1040); and/or motion within the texture region by fitting motion estimated between the texture region of the video picture and an adjacent picture to a two-dimensional polynomial The texture patch and the first set of parameters are then included into a bitstream which is output of the encoder and provided in this way to the decoder which reconstructs the texture based on the patch and the function applied to the patch.

Abstract: The present disclosure relates to encoding and decoding video by employing texture coding. In particular, a texture region is identified within a video picture and a texture patch is determined for the texture region. Moreover, a first set of parameters is derived specifying weighting factors for reconstructing spectral coefficients of the texture region by fitting the texture region in a spectral domain to a first function of the texture patch, the first function being defined by the first set of parameters. The texture patch and the first set of parameters are then included into a bitstream which is output by an encoder and provided in this way to the decoder which reconstructs the texture based on the patch and the function applied to the patch.

Abstract: The present disclosure relates to encoding a decoding video employing texture coding. In particular, a texture region is identified within a video picture and a texture patch is determined for said region. Moreover, a set of parameters specifies luminance within the texture region (1001) by fitting the texture region samples to a two-dimensional polynomial function of the patch determined according to the set of parameters (1040); and/or motion within the texture region by fitting motion estimated between the texture region of the video picture and an adjacent picture to a two-dimensional polynomial The texture patch and the first set of parameters are then included into a bitstream which is output of the encoder and provided in this way to the decoder which reconstructs the texture based on the patch and the function applied to the patch.

Abstract: A texture region is identified within a video picture, and a texture patch is determined for the region. Clustering is performed to identify a texture region within the video image. The clustering is further refined. In particular, one or more brightness parameters of a polynomial is determined by fitting the polynomial to the identified texture region. In the identified texture region, samples are detected with a distance to the fitted polynomial exceeding a first threshold. A refined texture region is identified as the texture region excluding one or more of the detected samples. The refined texture region is encoded separately from portions of the video image not belonging to the refined texture region.

Abstract: A method and an apparatus for generating superpixels for a sequence of images. A cluster assignment generator generates a cluster assignment for a first image of the sequence of images, e.g. by clustering pixels of the first image into superpixels or by retrieving an initial cluster assignment for the first image and processing only contour pixels with regard to their cluster assignment. A label propagator initializes subsequent images based on a label propagation using backward optical flow. A contour pixel processor then processes only contour pixels with regard to their cluster assignment for subsequent images of the sequence of images.

Abstract: A method for generating superpixels for an image comprising pixels and an apparatus configured to perform the method. A clustering stage clusters the pixels into initial clusters. A determination stage then selects spatially coherent parts of the clusters and determines unconnected fragments of the clusters. Pixels of these unconnected fragments are iteratively assigned to adjacent clusters by an assignment stage using a contour evolution process.

Abstract: Image super-resolution (SR) generally enhance the resolution of images. One of SR's main challenge is discovering mappings between low-resolution (LR) and high-resolution (HR) image patches. The invention learns patch upscaling projection matrices from a training set of images. Input images are divided into overlapping patches, which are normalized and transformed to a defined orientation. Different transformations can be recognized and dealt with by using a simple 2D-projection. The transformed patches are clustered, and cluster specific upscaling projection matrices and corresponding cluster centroids determined during training are applied to obtain upscaled patches. The upscaled patches are assembled to an upscaled image.

Abstract: A method and an apparatus for generating an initial superpixel label map for a current image from an image sequence are described. The apparatus includes a feature detector that determines features in the current image. A feature tracker then tracks the determined features back into a previous image. Based on the tracked features a transformer transforms a superpixel label map associated to the previous image into an initial superpixel label map for the current image.

Abstract: Image super-resolution (SR) generally enhance the resolution of images. One of SR's main challenge is discovering mappings between low-resolution (LR) and high-resolution (HR) image patches. The invention learns patch upscaling projection matrices from a training set of images. Input images are divided into overlapping patches, which are normalized and transformed to a defined orientation. Different transformations can be recognized and dealt with by using a simple 2D-projection. The transformed patches are clustered, and cluster specific upscaling projection matrices and corresponding cluster centroids determined during training are applied to obtain upscaled patches. The upscaled patches are assembled to an upscaled image.

Abstract: A method and an apparatus for life cycle management for superpixels associated to frames of a sequence of frames are described. An area occupied by a superpixel in a frame of the sequence of frames is monitored. In case the area of the superpixel becomes smaller than a specified first value, the superpixel is terminated in the later frame. In case the area of the superpixel becomes larger than a specified second value, the superpixel is split in the later frame.

Abstract: A method for generating superpixels for an image comprising pixels and an apparatus configured to perform the method. A clustering stage clusters the pixels into initial clusters. A determination stage then selects spatially coherent parts of the clusters and determines unconnected fragments of the clusters. Pixels of these unconnected fragments are iteratively assigned to adjacent clusters by an assignment stage using a contour evolution process.

Abstract: A method and an apparatus for generating superpixels for a sequence of images. A cluster assignment generator generates a cluster assignment for a first image of the sequence of images, e.g. by clustering pixels of the first image into superpixels or by retrieving an initial cluster assignment for the first image and processing only contour pixels with regard to their cluster assignment. A label propagator initializes subsequent images based on a label propagation using backward optical flow. A contour pixel processor then processes only contour pixels with regard to their cluster assignment for subsequent images of the sequence of images.

Abstract: A method and an apparatus for life cycle management for superpixels associated to frames of a sequence of frames are described. An area occupied by a superpixel in a frame of the sequence of frames is monitored. In case the area of the superpixel becomes smaller than a specified first value, the superpixel is terminated in the later frame. In case the area of the superpixel becomes larger than a specified second value, the superpixel is split in the later frame.

Abstract: A method and an apparatus for generating superpixels for a sequence of frames are presented. A feature space of the sequence of frames is separated into a color subspace and a spatial subspace. A clustering is then performed that comprises iterative assigning and updating.

Abstract: A method and an apparatus for life cycle management for superpixels associated to frames of a sequence of frames are described. An area occupied by a superpixel in a frame of the sequence of frames is monitored. In case the area of the superpixel becomes smaller than a specified first value, the superpixel is terminated in the later frame. In case the area of the superpixel becomes larger than a specified second value, the superpixel is split in the later frame.

Abstract: A method and an apparatus for multi-label segmentation of an image are described. In a first step user defined labels are determined for one or more pixels of the image. Then a fraction of the pixels of the image for which no user defined label is determined is pre-initialized. Finally, a cellular automaton-based segmentation of the image is performed using the user defined labels and the pre-initialized pixels.

Abstract: A method and an apparatus for multi-label segmentation of an image are described. First an energy function is determined for the image. Then for a homogeneous region of the image variables of the energy function are grouped to a single variable. Subsequently the energy function is minimized and labels are assigned to regions of the image based on the minimized energy function.

Abstract: A method and an apparatus for life cycle management for superpixels associated to frames of a sequence of frames are described. An area occupied by a superpixel in a frame of the sequence of frames is monitored. In case the area of the superpixel becomes smaller than a specified first value, the superpixel is terminated in the later frame. In case the area of the superpixel becomes larger than a specified second value, the superpixel is split in the later frame.

Abstract: A method and an apparatus for generating superpixels for a sequence of frames are described. A feature space of the sequence of frames is separated into a color subspace and a spatial subspace. A clustering is then performed in the spatial subspace on a frame basis. In the color subspace a clustering is performed on stacked frames.