Abstract: The present invention relates to a method for pruning a neural network comprising a plurality of neurons, said method comprising: an initialization phase, wherein input information is fetched comprising at least parameters ({wni,bni}) related to said neural network and a dataset (D) representative of a task that said neural network has to deal with, wherein said parameters ({wni,bni}) comprising a weights vector (wni) and/or a bias (bni) related to at least one neuron of said plurality of neurons; a regularization phase, wherein said neural network is trained according to a training algorithm by using said dataset (D); a thresholding phase, wherein an element (wnij) of said weights vector (wni) is put at zero when its absolute value is below a given threshold (T).

Abstract: A method for encoding digital images or video streams, includes a receiving phase, wherein a portion of an image is received; a graph weights prediction phase, wherein the elements of a weights matrix associated to the graph related to the blocks of the image (predicted blocks) are predicted on the basis of reconstructed, de-quantized and inverse-transformed pixel values of at least one previously coded block (predictor block) of the image, the weights matrix being a matrix comprising elements denoting the level of similarity between a pair of pixels composing said image, a graph transform computation phase, wherein the graph Fourier transform of the blocks of the image is performed, obtaining for the blocks a set of coefficients determined on the basis of the predicted weights; a coefficients quantization phase, wherein the coefficients are quantized an output phase wherein a bitstream comprising the transformed and quantized coefficients is transmitted and/or stored.

Abstract: The present invention relates to a method for encoding the borders of pixel regions of an image, wherein the borders contain a sequence of vertices subdividing the image into regions of pixels (superpixels), by generating a sequence of symbols from an alphabet including the step of: defining for each superpixel a first vertex for coding the borders of the superpixel according to a criterion common to all superpixels; defining for each superpixel the same coding order of the border vertices, either clockwise or counter-clockwise; defining the order for coding the superpixels on the base of a common rule depending on the relative positions of the first vertices; defining a set of vertices as a known border, wherein the following steps are performed for selecting a symbol of the alphabet, for encoding the borders of the superpixels: a) determining the first vertex of the next superpixel border individuated by the common criterion; b) determining the next vertex to be encoded on the basis of the coding direction;

Abstract: A method and an apparatus for encoding and/or decoding digital images or video streams are provided, wherein the encoding apparatus includes a processor configured for reading at least a portion of the image, segmenting the portion of the image in order to obtain groups of pixels identified by borders information and containing at least two pixels having one or more homogeneous characteristics, computing, for each group of pixels, a weight map on the basis of the borders information associated to the group of pixels, a graph transform matrix on the basis of the weight map, and transform coefficients on the basis of the graph transform matrix (U) and of the pixels contained in the group of pixels.

Abstract: The present invention relates to a method for encoding the borders of pixel regions of an image, wherein the borders contain a sequence of vertices subdividing the image into regions of pixels (superpixels), by generating a sequence of symbols from an alphabet including the step of: defining for each superpixel a first vertex for coding the borders of the superpixel according to a criterion common to all superpixels; defining for each superpixel the same coding order of the border vertices, either clockwise or counter-clockwise; defining the order for coding the superpixels on the base of a common rule depending on the relative positions of the first vertices; defining a set of vertices as a known border, wherein the following steps are performed for selecting a symbol of the alphabet, for encoding the borders of the superpixels: a) determining the first vertex of the next superpixel border individuated by the common criterion; b) determining the next vertex to be encoded on the basis of the coding direction;

Abstract: A method for encoding digital images or video streams, includes a receiving phase, wherein a portion of an image is received; a graph weights prediction phase, wherein the elements of a weights matrix associated to the graph related to the blocks of the image (predicted blocks) are predicted on the basis of reconstructed, de-quantized and inverse-transformed pixel values of at least one previously coded block (predictor block) of the image, the weights matrix being a matrix comprising elements denoting the level of similarity between a pair of pixels composing said image, a graph transform computation phase, wherein the graph Fourier transform of the blocks of the image is performed, obtaining for the blocks a set of coefficients determined on the basis of the predicted weights; a coefficients quantization phase, wherein the coefficients are quantized an output phase wherein a bitstream comprising the transformed and quantized coefficients is transmitted and/or stored.

Abstract: A method and an apparatus for encoding and/or decoding digital images or video streams are provided, wherein the encoding apparatus includes a processor configured for reading at least a portion of the image, segmenting the portion of the image in order to obtain groups of pixels identified by borders information and containing at least two pixels having one or more homogeneous characteristics, computing, for each group of pixels, a weight map on the basis of the borders information associated to the group of pixels, a graph transform matrix on the basis of the weight map, and transform coefficients on the basis of the graph transform matrix (U) and of the pixels contained in the group of pixels.

Abstract: Devices and methods for generating a three-dimensional video stream starting from a sequence of video images. The sequence includes a first view (V0), at least one second view (V1) of a scene, and a depth map (D0) of said first view (V0), or a disparity map of said at least one second view (V1) with respect to the first view (V0). At least one occlusion image (O1) including the occluded pixels of said second view (V1) is obtained by starting from said depth map (D0) or from said disparity map. A compacted occlusion image (OC1)is generated by spatially repositioning said occluded pixels of said at least one occlusion image (O1), so as to move said pixels closer to one another. The three-dimensional video stream may include said first view (V0), said depth map (D0) or said disparity map, and said at least one compacted occlusion image (OC1).

Abstract: A method for edge correction of images of a three-dimensional video content, the video content including at least one original view image and at least one depth or disparity map, the method including the following steps: detecting edges in at least one original view image for obtaining original edges; warping the original edges according to the depth or disparity map; detecting a set of warped edges altered by the warping process; and correcting the altered edges for obtaining corrected edges.

Abstract: A method is described for generating a color image composed of a plurality of components (Y, U, V) by starting from at least one depth or disparity map (DM1, DM2), wherein a first set of pixels of said at least one depth or disparity map (DM1, DM2) is entered into the luminance component (Y) of said color image, and wherein a second and a third sets of pixels of said at least one depth or disparity map (DM1, DM2) are entered into the two chrominance components (U, V) of said color image.

Abstract: A method for edge correction of images of a three-dimensional video content, the video content including at least one original view image and at least one depth or disparity map, the method including the following steps: detecting edges in at least one original view image for obtaining original edges; warping the original edges according to the depth or disparity map; detecting a set of warped edges altered by the warping process; and correcting the altered edges for obtaining corrected edges.

Abstract: A method is described for generating a three-dimensional video stream by starting from a sequence of video images, said sequence including a first view (V0), at least one second view (V1) of a scene, as well as a depth map (D0) of said first view (V0), or a disparity map of said at least one second view (V1) with respect to the first view (V0), the method including, for one image, the following steps: obtaining at least one occlusion image (O1) including the occluded pixels of said second view (V1) by starting from said depth map (D0) or from said disparity map; generating a compacted occlusion image (OC1) by spatially repositioning said occluded pixels of said at least one occlusion image (O1), so as to move said pixels closer to one another; said three-dimensional video stream including, for one image, said first view (V0), said depth map (D0) or said disparity map, and said at least one compacted occlusion image (OC1).

Abstract: A method is described for generating a colour image composed of a plurality of components (Y, U, V) by starting from at least one depth or disparity map (DM1, DM2), wherein a first set of pixels of said at least one depth or disparity map (DM1, DM2) is entered into the luminance component (Y) of said colour image, and wherein a second and a third sets of pixels of said at least one depth or disparity map (DM1, DM2) are entered into the two chrominance components (U, V) of said colour image.