公开(公告)号：US20250088648A1

公开(公告)日：2025-03-13

申请号：US18758390

申请日：2024-06-28

Applicant: SISVEL TECHNOLOGY S.R.L. ,  UNIVERSITÀ DEGLI STUDI DI TORINO ,  INSTITUT MINES TELECOM

Inventor： Alberto Presta ,  Attilio Fiandrotti ,  Enzo Tartaglione ,  Marco Grangetto

IPC: H04N19/42 ,  G06N3/0455 ,  H04N19/124 ,  H04N19/91

Abstract: A method for learned image compression implemented in an autoencoder including a learnable encoder and a decoder, the method including: a) extracting from an image a latent space by the learnable encoder; b) quantizing the latent space by a quantizer to obtain a quantized latent space; c) entropy coding the quantized latent space by an entropy encoder to obtain a bitstream, wherein an entropy model used to encode the latent space is represented by a probability distribution; d) entropy decoding the bitstream by an entropy decoder to obtain an entropy decoded bitstream; e) feeding the entropy decoded bitstream to the decoder; f) recover a reconstructed image by the decoder; g) training the autoencoder via standard gradient descent of the backpropagated error gradient by finding learnable parameters of the learnable encoder and of the decoder that minimize a rate distortion cost function, wherein the entropy encoder is based on a differentiable formulation of a soft frequency counter.

公开(公告)号：US11432012B2

公开(公告)日：2022-08-30

申请号：US16488851

申请日：2018-03-02

Applicant: SISVEL TECHNOLOGY S.R.L.

Inventor： Marco Grangetto ,  Francesco Verdoja

IPC: H04N19/61 ,  H04N19/124 ,  H04N19/176 ,  H04N19/91 ,  H04N19/44

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.

公开(公告)号：US11012692B2

公开(公告)日：2021-05-18

申请号：US15768450

申请日：2016-10-13

Applicant: SISVEL TECHNOLOGY S.R.L.

Inventor： Giulia Fracastoro ,  Enrico Magli

IPC: H04N19/12 ,  H04N19/625 ,  H04N19/176 ,  H04N19/147 ,  H04N19/122 ,  H04N19/139 ,  H04N19/18 ,  H04N19/196 ,  H04N19/61

Abstract: A method and an apparatus are provided for encoding and/or decoding digital images or video streams. The encoding apparatus includes a processor configured for reading at least a portion of an image (f), determining a rotation angle (θ) on the basis of the portion of the image (f), determining rotated transform matrix (V′) which is the result of a rotation of at least one basis vector of a Discrete Cosine Transform matrix (V) by the rotation angle (θ), computing transformed coefficients (f{circumflex over ( )}) on the basis of the pixel values contained in the portion of the image (f) and the rotated transform information (V′), outputting the transformed coefficients (f{circumflex over ( )}) to the destination.

公开(公告)号：US10708601B2

公开(公告)日：2020-07-07

申请号：US16488879

申请日：2018-03-02

Applicant: SISVEL TECHNOLOGY S.R.L.

Inventor： Marco Grangetto ,  Francesco Verdoja

IPC: H04N19/00 ,  H04N19/167 ,  H04N19/103 ,  H04N19/182 ,  G06T15/00 ,  G06T17/00

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; c) selecting a first symbol (“0”) for encoding the next vertex if the next vertex of a border pertains to the known border, d) selecting a symbol (“1”; “2”) different from the first symbol (“0”) if the next vertex is not in the known border; e) repeating steps b), c), d) and e) until all vertices of the superpixel border have been encoded; f) adding each vertex of the superpixel border that was not in the known border to the set; g) determining the next superpixel whose border is to be encoded according to the common rule, if any; i) repeating steps a)-g) until the borders of all the superpixels of the image have being added to the known border.

公开(公告)号：US20200014937A1

公开(公告)日：2020-01-09

申请号：US16488879

申请日：2018-03-02

Applicant: SISVEL TECHNOLOGY S.R.L.

Inventor： Marco GRANGETTO ,  Francesco VERDOJA

IPC: H04N19/167 ,  H04N19/182 ,  H04N19/103

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; c) selecting a first symbol (“0”) for encoding the next vertex if the next vertex of a border pertains to the known border, d) selecting a symbol (“1”; “2”) different from the first symbol (“0”) if the next vertex is not in the known border; e) repeating steps b), c), d) and e) until all vertices of the superpixel border have been encoded; f) adding each vertex of the superpixel border that was not in the known border to the set; g) determining the next superpixel whose border is to be encoded according to the common rule, if any; i) repeating steps a)-g) until the borders of all the superpixels of the image have being added to the known border.

公开(公告)号：US10175053B2

公开(公告)日：2019-01-08

申请号：US14346245

申请日：2012-09-21

Applicant: SISVEL TECHNOLOGY S.R.L.

Inventor： Saverio Celia

IPC: G01C21/34 ,  G06F17/30 ,  G01C21/32

Abstract: A method for managing a map (140) stored in a memory (130) associated with a personal navigation device (10), including a command and data entry unit (115) operable by a user, wherein the map (140) can be visualized on a display (115) and includes a road network, the method including the step of combining a first set of data about the road network, stored in the map (140), with a second set of data about at least one road not present in the road network or defined as not viable, in particular a new road, wherein the second data can be entered by the user by the command and data entry unit (115).

公开(公告)号：US20180278957A1

公开(公告)日：2018-09-27

申请号：US15762496

申请日：2016-09-23

Applicant: SISVEL TECHNOLOGY S.R.L. ,  POLITECNICO DI TORINO

Inventor： Giulia Fracastoro ,  Enrico Magli ,  Francesco Verdoja ,  Marco Grangetto

IPC: H04N19/60 ,  H04N19/17 ,  G06K9/34 ,  G06T7/11 ,  H04N19/182

CPC classification number: H04N19/60 ,  G06K9/34 ,  G06K9/6224 ,  G06T7/11 ,  H04N19/17 ,  H04N19/182

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.

公开(公告)号：US11122298B2

公开(公告)日：2021-09-14

申请号：US16465926

申请日：2017-11-29

Applicant: SISVEL TECHNOLOGY S.R.L. ,  ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL)

Inventor： Giulia Fracastoro ,  Dorina Thanou ,  Pascal Frossard

IPC: H04N19/625 ,  H04N19/122 ,  H04N19/17 ,  G06K9/52

Abstract: A method and an apparatus for encoding and/or decoding digital images, wherein the encoding apparatus includes a processor configured for determining weights of a graph related to an image by minimizing a cost function, transforming the weights through a graph Fourier transform, quantizing the transformed weights, computing transformed coefficients through a graph Fourier transform of a graph having the transformed weights as weights, de-quantizing the quantized transformed weights, computing a reconstructed image through an inverse graph Fourier transform on the basis of the de-quantized transformed weights, computing a distortion cost on the basis of the reconstructed image and the original image, generating a final encoded image on the basis of the distortion cost.

公开(公告)号：US10887608B2

公开(公告)日：2021-01-05

申请号：US16610751

申请日：2018-05-03

Applicant: SISVEL TECHNOLOGY S.R.L.

Inventor： Yung-Hsuan Chao ,  Gene Cheung ,  Antonio Ortega

IPC: H04N19/46 ,  H04N19/176 ,  H04N19/117 ,  H04N19/182 ,  H04N13/229 ,  H04N13/232 ,  H04N13/161

Abstract: A method for encoding a raw lenselet image includes a receiving phase, wherein at least a portion of a raw lenselet image is received, the image including a plurality of macro-pixels, each macro-pixel having pixels corresponding to a specific view angle for the same point of a scene, and an output phase, wherein a bitstream having at least a portion of an encoded lenselet image is outputted. The method has an image transform phase, wherein the pixels of said raw lenselet image are spatially displaced in a transformed multi-color image having a larger number of columns and rows with respect to the received raw lenselet image, wherein dummy pixels having undefined value are inserted into the raw lenselet image and wherein the displacement is performed so as to put the estimated center location of each macro-pixel onto integer pixel locations. Moreover, the method includes a sub-view generation phase, wherein a sequence of sub-views is generated, said sub-views having pixels of the same angular coordinates extracted from different macro-pixels of the transformed raw lenselet image. Finally, the method has a graph coding phase, wherein a bitstream is generated by encoding a graph representation of at least one of the sub-views of the sequence according to a predefined graph signal processing technique.

公开(公告)号：US20200228840A1

公开(公告)日：2020-07-16

申请号：US16465926

申请日：2017-11-29

Applicant: SISVEL TECHNOLOGY S.R.L. ,  ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL)

Inventor： Giulia Fracastoro ,  Dorina Thanou ,  Pascal Frossard

IPC: H04N19/625 ,  H04N19/122 ,  H04N19/17 ,  G06K9/52

Abstract: A method and an apparatus for encoding and/or decoding digital images, wherein the encoding apparatus includes a processor configured for determining weights of a graph related to an image by minimizing a cost function, transforming the weights through a graph Fourier transform, quantizing the transformed weights, computing transformed coefficients through a graph Fourier transform of a graph having the transformed weights as weights, de-quantizing the quantized transformed weights, computing a reconstructed image through an inverse graph Fourier transform on the basis of the de-quantized transformed weights, computing a distortion cost on the basis of the reconstructed image and the original image, generating a final encoded image on the basis of the distortion cost.