EP4222957A1 - Procédé et dispositif électronique de décodage d'un flux de données, programme d'ordinateur et flux de données associés - Google Patents
Procédé et dispositif électronique de décodage d'un flux de données, programme d'ordinateur et flux de données associésInfo
- Publication number
- EP4222957A1 EP4222957A1 EP21785841.4A EP21785841A EP4222957A1 EP 4222957 A1 EP4222957 A1 EP 4222957A1 EP 21785841 A EP21785841 A EP 21785841A EP 4222957 A1 EP4222957 A1 EP 4222957A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- data
- decoding
- context
- sequence
- map
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
- H04N19/13—Adaptive entropy coding, e.g. adaptive variable length coding [AVLC] or context adaptive binary arithmetic coding [CABAC]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/90—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using coding techniques not provided for in groups H04N19/10-H04N19/85, e.g. fractals
- H04N19/91—Entropy coding, e.g. variable length coding [VLC] or arithmetic coding
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
- H03M7/60—General implementation details not specific to a particular type of compression
- H03M7/6005—Decoder aspects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0495—Quantised networks; Sparse networks; Compressed networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
- G06T9/002—Image coding using neural networks
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
- H03M7/3066—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction by means of a mask or a bit-map
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
- H03M7/3068—Precoding preceding compression, e.g. Burrows-Wheeler transformation
- H03M7/3079—Context modeling
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/136—Incoming video signal characteristics or properties
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Definitions
- the present invention relates to the technical field of data decoding.
- It relates in particular to a method and an electronic device for decoding a data stream, as well as a computer program and an associated data stream.
- Entropy coding is used, particularly in the field of audio or video content coding, to optimally compress data by taking into account the appearance statistics of the different symbols in this data.
- CABAC coding for "Context-based adaptive binary arithmetic coding" is known in this context as described in the article "Context-based adaptive binary arithmetic coding in the H.264/AVC video compression standard', by D. Marpe, H. Schwarz, and T. Wiegand, in IEEE Transactions on Circuits and Systems for Video Technology, vol.13, no.7, pp. 620-636, July 2003.
- the entropy decoder When it is used for the entropy coding or the entropy decoding of data within the framework of a standard (for example a standard defining a way of compressing an audio or video content), the entropy decoder is at each moment parameterized in a context which depends, in a predefined manner in the standard concerned, on the previously coded or decoded syntax elements.
- a standard for example a standard defining a way of compressing an audio or video content
- the present invention proposes a method for decoding a data stream comprising a plurality of identifiers and a sequence of binary elements, into a series of data of predetermined respective types, the method comprising the following steps for obtaining each datum of said after :
- the data obtained are for example values representative of an audio or video content. These representative values can be produced, during a coding process, by a coding artificial neural network, as described below (or, more generally, by a machine learning process such as a deep learning process or a decision tree forest learning process).
- the data stream can also include information indicative of a set of contexts that can be used within the entropy decoder. Such information is for example indicative of a number of contexts that can be used within the entropy decoder.
- the data stream can also comprise, for each context that can be used within the entropy decoder, parameterization data of the context concerned.
- the decoding method can then include a step of initializing each usable context within the entropy decoder by means of the parametrization data of the context concerned.
- the aforementioned indicative information and the parameterization data thus make it possible to configure the entropy decoder before effective implementation of the entropy decoding.
- the decoding method may also comprise a step of applying the data obtained as input to an artificial neural network.
- Such an artificial neural network is for example implemented by a processing unit (possibly a parallelized processing unit).
- the method can then include a step of configuring the processing unit according to data included in the data stream.
- the invention is particularly interesting in this context where the technical nature of each of the various manipulated data (or representative values) depends on the artificial neural network used (defined for its part by data which have just been mentioned) and is not therefore not predetermined, so that the context used for the entropy coding of a particular datum does not cannot be defined in advance (as already indicated, such a prior definition can for example be given in a standard).
- the invention is however not limited to this context and is of interest since the respective association of the data to be coded and of the entropy coding contexts cannot be defined in advance.
- the invention can be used advantageously for the entropic coding of texts written in several languages using different alphabets.
- the number of signs of the alphabet and the probability of appearance of these being different in each language, the invention makes it possible in such a situation to specify the context to be used for the entropic coding of the signs or words specific to a tongue.
- the decoding method can moreover comprise an automatic learning method, such as a deep learning method (or “deep learning” according to the Anglo-Saxon name often used) or a forest learning method. of decision trees (or "random forest') according to the Anglo-Saxon application often used).
- the data stream can then include data for configuring this automatic learning process and/or a configuration step a processing unit by means of these configuration data so as to implement this automatic learning method.
- the invention can be used to code data from a neural network or to decode data to be supplied to a neural network.
- a neural network is understood as a processing process comprising a large number of similar steps, only the parameters of these steps being different from each other, and fixed by a learning process, the steps being adapted to be implemented in a massively parallel.
- a neural network can designate a series of layers carrying out a linear filtering of the data coming from the input layer or the previous layer, each filtering being followed by the application of a nonlinear function (neural network to the classical sense).
- a neural network can designate a series of tests, the result of each test determining the next tests to be applied (forest of decision trees), or other processing processes having the aforementioned characteristic.
- the aforementioned data sequence forms a set of characteristic maps.
- the identifiers of the plurality of identifiers are respectively associated with the feature maps of the set of feature maps. Provision can be made in this case for the context determined for obtaining an element of a given map of characteristics to be determined on the basis of the identifier associated with the given map of characteristics.
- the identifiers of the plurality of identifiers can be respectively associated with the different positions in the common structure. Provision can then be made for the context determined for obtaining a given element of a map of characteristics to be determined on the basis of the identifier associated with the position defining this given element.
- the invention also proposes an electronic device for decoding a data stream comprising a plurality of identifiers and a sequence of binary elements, into a sequence of data of predetermined respective types, the electronic device comprising an entropy decoder receiving as input the sequence of binary elements, and a configuration module designed to determine a context on the basis of an identifier associated, among the plurality of identifiers, with the type of data to be obtained, and to configure the entropy decoder in the context determined so as to obtain said datum at the output of the entropy decoder.
- the invention further proposes a computer program comprising instructions executable by a processor and designed to implement a decoding method as proposed above when these instructions are executed by the processor.
- the invention finally proposes a data stream representing a series of data of predetermined respective types, and comprising a plurality of identifiers and a sequence of binary elements, each identifier being representative of a context in which an entropy decoder is configured to obtaining, when this entropy decoder receives as input part of the sequence of binary elements, at least one datum having a type associated with this identifier.
- FIG. 1 shows an electronic coding device used in the context of the invention
- FIG. 2 schematically illustrates maps of characteristics used by the electronic coding device of Figure 1;
- FIG. 3 is a flowchart representing the steps of an encoding method implemented within the electronic encoding device of Figure 1;
- FIG. 4 shows the data stream produced by the electronic encoding device of Figure 1;
- FIG. 5 shows an example of an electronic decoding device according to the invention.
- FIG. 6 is a flowchart representing the steps of a decoding method implemented within the electronic decoding device of Figure 5.
- FIG. 1 represents an electronic coding device 2 including an entropy coder 10.
- This electronic coding device 2 comprises a processor 4 (for example a microprocessor) and a parallelized processing unit 6, for example a graphics processing unit (or GPU for "Graphical Processing Unit') or a tensor processing unit (or TPU for "Tensor Processing Unit”).
- a processor 4 for example a microprocessor
- a parallelized processing unit 6 for example a graphics processing unit (or GPU for "Graphical Processing Unit') or a tensor processing unit (or TPU for "Tensor Processing Unit”).
- the processor 4 is programmed (for example by means of computer program instructions executable by the processor 4 and stored in a memory - not shown - associated with the processor 4) to implement a control module 5 and the entropic encoder 10 already mentioned.
- control module 5 receives data P, B representing audio or video content to be compressed, here format data P and content data B.
- the format data P indicates characteristics of the format for representing the audio or video content, for example for a video content the dimensions (in pixels) of the images, the frame rate, the bit depth of the luminance information and the bit depth of the chrominance information.
- the content data B forms a representation (here uncompressed) of the audio or video content.
- the content data includes, for each pixel of each image of a sequence of images, data representing a luminance value of the pixel and data representing chrominance values of the pixels.
- the parallelized processing unit 6 is designed to implement an artificial neural network 8 after having been configured by the processor 4 (for example by the control module 5). To do this, the parallelized processing unit 6 is designed to perform in parallel at a given instant a plurality of operations of the same type.
- the artificial neural network 8 is used in the context of processing the content data B aimed at obtaining values V representative of the audio or video content.
- the artificial neural network 8 when the content data B is input to the artificial neural network 8, the artificial neural network 8 outputs the representative values V.
- the content data B applied at the input of the artificial neural network 8 can represent a block of an image, or a block of a component of an image (for example a block of a luminance or chrominance component of this image, or a block of a color component of this image), or an image of a video sequence, or a component of an image of a video sequence (for example a luminance or chrominance component, or a color component), or else a series of images of the video sequence.
- the processing of content data B may comprise the use of several artificial neural networks, as described for example in the aforementioned article 'DVC: An End-to-end Deep Video Compression Framework', by Guo Lu and al., 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
- the representative values V produced at the output of the artificial neural network 8 are here organized into a sequence of feature maps F (or "feature maps" according to the Anglo-Saxon name sometimes used), as schematically represented in FIG. 2.
- the network of artificial neurons 8 produces for example here N maps of characteristics F.
- Each feature map F has for example a two-dimensional structure (or matrix structure).
- each feature map F here forms a matrix with H rows and W columns.
- An element located at a given position in a given feature map F corresponds to the representative value V produced by an output node (or node of the output layer) of the artificial neural network, this output node being associated in a predefined manner at this given position and at this given F feature map.
- the artificial neural network 8 produces as output (that is to say on its output layer) at a given instant all of the N maps of characteristics.
- different sets of content data B are applied at different times at the input (i.e.
- the network of artificial neurons 8 produces at each of these different instants at output (that is to say on its output layer) a corresponding map of characteristics F (the output nodes of the artificial neural network 8 being in this case associated respectively with the different positions of a single map of characteristics F).
- the representative values V produced at the output of the artificial neural network 8 can be organized into an ordered sequence of representative values V.
- the ordered sequence of representative values V produced at the output of the artificial neural network 8 is associated with this block.
- the different sequences of representative values successively produced by the artificial neural network 8 are thus respectively associated with the different blocks of the image (or with the different blocks of the relevant component of the image).
- the representative values V produced at the output of the artificial neural network 8 are placed within a data structure with several dimensions (for example M dimensions). Each element of this structure is then identified by its position within the structure, namely in the aforementioned example by means of an M-tuple of coordinates.
- a representative value V produced by a given output node (that is to say by a given node of the output layer) of the artificial neural network 8 then forms an element of the structure designated by a position within the structure associated in a predefined manner with this output node (that is to say by coordinates associated in a predefined manner with this output node).
- the representative values V produced at the output of the artificial neural network 8 are applied to the input of the entropic encoder 10.
- These representative values V are for example applied in a predefined order.
- the representative values V are organized into an (ordered) sequence of feature maps F
- the different feature maps F are applied one after the other (in the sequence order mentioned above), and the different elements of the same map of characteristics F (which each correspond to a representative value) are applied according to a predefined scheme (according to their position) within the map of characteristics F.
- the entropic coder 10 is designed to code several statistical sources each corresponding to a particular probability of appearance of the symbols to be coded. To do this, the entropy coder 10 can be parameterized in a particular context, associated with a given statistical source and in which the entropy coder 10 produces an optimal entropy code if the symbols actually coded (here the representative values V) respect the expected probability for this statistical source.
- the entropy coder 10 is here a coder of the CABAC type (for "Context-based adaptive binary arithmetic coding"). As a variant, it could be another type of entropy coder, for example a Huffman type coder, an arithmetic coder or an LZW coder (for “Lempel-Ziv-Welch”). As explained below, the entropic encoder 10 is parameterized at each instant by the control module 5 in a context C which depends on the type of the representative value V to be coded at this instant (representative value V coming from the artificial neural network 8 ).
- the context C selected by the control module 5 to parameterize the entropy coder 10 with a view to the entropy coding of an element of a map of characteristics F can for example depend (in a predefined manner) on the map of characteristics F concerned and/or on the position of the element in the map of characteristics F.
- the association of a certain context with a map of characteristics and/or at a position in the feature map is carried out for example by means of prior statistical measurements, for a large number of images processed by means of the artificial coding neural network 8, of the probability of appearance of the symbols in this map of characteristics or at this position.
- the purpose of such an association is to isolate the different statistical sources within the representative values V so as to code each of these sources statistics with a specific context, and thus maximize compression.
- the entropy encoder 10 produces at output a sequence of binary elements (or sequence of bits) Fnn.
- the method of FIG. 3 begins with a step E2 of selecting an encoding process - decoding process couple.
- the coding process and the decoding process each use at least one artificial neural network.
- the coding process is implemented by a coding artificial neural network and the decoding process is implemented by a decoding artificial neural network.
- the assembly formed by the artificial coding neural network and by the artificial decoding neural network constitutes for example a self -encoder.
- the coding process - decoding process pair is for example selected from a plurality of predefined coding process - decoding process pairs, that is to say here from a plurality of pairs of artificial neural network coding - network of artificial decoding neurons.
- the coding process-decoding process pair can for example be selected from coding process-decoding process pairs for which the decoding process uses an artificial neural network available for an electronic decoding device (such as the electronic decoding 20 represented in FIG. 5 and described below).
- the electronic coding device may optionally receive beforehand (from the electronic decoding device or from a dedicated server) a list of artificial neural networks accessible by this electronic decoding device.
- the coding process/decoding process couple can also be selected according to the intended application (indicated for example by a user by means of a user interface (not shown) of the electronic coding device 2). For example, if the target application is a videoconference, the pair of coding process - decoding process selected includes a low-latency decoding process. In other applications, the pair of coding process - decoding process selected will include a random access decoding process.
- an image of the video sequence is for example represented by coded data which can be sent and decoded immediately; the data can then be sent in the order in which the video images are displayed, which in this case guarantees a latency of one image between encoding and decoding.
- the coded data relating respectively to a plurality of images are sent in an order different from the display order of these images, which makes it possible to increase the compression .
- Images coded without reference to the other images can then be coded regularly, which makes it possible to start the decoding of the video sequence from several places in the coded stream.
- HEVC High Efficiency Video Coding
- the different criteria for selecting the coding process/decoding process couple can optionally be combined.
- control module 5 proceeds in step E4 to configure the parallelized processing unit 6 so that the parallelized processing unit 6 can implement the process. coding selected.
- This step E4 comprises in particular the instantiation, within the parallelized processing unit 6, of the coding artificial neural network 8 used by the selected coding process.
- This instantiation may include the following steps:
- the method of FIG. 3 then comprises a step E6 of implementing the coding process, that is to say here a step of applying the content data B as input to the coding artificial neural network 8 (or in other words a step of activating the coding artificial neural network 8 by taking the content data B as input).
- Step E6 thus makes it possible to produce (here at the output of the coding artificial neural network 8) the representative values V.
- the following steps aim at the coding (that is to say the preparation) of the data stream intended for the electronic decoding device (for example the electronic decoding device 20 described below with reference to FIG. 5).
- the method thus notably comprises a step E8 of encoding a first header part Fc which comprises data characteristic of the format of representation of the audio or video content (here for example data linked to the format of the video sequence being encoded).
- These data forming the first header part Fc indicate for example the dimensions (in pixels) of the images, the frame rate, the bit depth of the luminance information and the bit depth of the chrominance information. These data are for example constructed on the basis of the data of format P mentioned above (after a possible reformatting).
- the control module 5 proceeds in step E10 to the coding of a second header part comprising data R indicative of the decoding artificial neural network (associated with the pair of coding process - decoding process selected at the step E2).
- these indicative data R can comprise an identifier of the decoding artificial neural network.
- Such an identifier designates (from among a plurality of artificial decoding neural networks, for example among all the artificial decoding neural networks available for the electronic decoding device) the artificial decoding neural network corresponding to the artificial neural network of coding 8 mentioned above, artificial neural network of decoding which must therefore be used for the decoding of the representative values V.
- such an identifier defines by convention (shared in particular by the electronic coding device and the electronic decoding device) this artificial decoding neural network, for example within the set of artificial decoding neural networks available for (or accessible by) the electronic decoding device.
- the electronic coding device 2 may optionally receive beforehand (from the electronic decoding device or from a dedicated server) a list of artificial neural networks accessible by the electronic decoding device.
- these indicative data R can comprise descriptive data of the decoding artificial neural network.
- the decoding artificial neural network (corresponding to the aforementioned coding artificial neural network 8) is for example coded (that is to say represented) by these descriptive data (or coding data of the artificial decoding neurons) in accordance with a standard such as the MPEG-7 standard part 17 or in a format such as the JSON format.
- the indicative data R can also be made for the indicative data R to include an indicator indicating whether the decoding artificial neural network is part of a predetermined set of artificial neural networks (in which case the first possibility of embodiment mentioned above is used) or whether the decoding artificial neural network is encoded in the data stream, that is to say represented by means of the aforementioned descriptive data (in which case the second possibility of embodiment mentioned above is used).
- the method of FIG. 3 continues with a step E12 of determining the possibility for the electronic decoding device to implement the decoding process using the decoding artificial neural network.
- the control module 5 determines for example this possibility by determining (possibly by means of prior exchanges between the electronic coding device 2 and the electronic decoding device) whether the electronic decoding device comprises a module adapted to implement this process decoding or software adapted to the implementation of this decoding process by the electronic decoding device when this software is executed by a processor of the electronic decoding device.
- control module 5 determines that it is possible for the electronic decoding device to implement the decoding process, the method continues at step E16 described below.
- step E14 If the control module 5 determines that it is not possible for the electronic decoding device to implement the decoding process, the method performs step E14 described below (before going to step E16 ).
- step E14 could be made on another criterion, for example as a function of an indicator dedicated stored within the electronic coding device 2 (and optionally adjustable by the user via a user interface of the electronic coding device 2) or according to a choice of the user (obtained for example via a user interface of the device electronic coding 2).
- the control module 5 encodes in the data stream at step E14 a third header part containing a computer program Exe (or code) executable by a processor of the electronic decoding device. (The use of the Exe computer program within the electronic decoding device is described below with reference to Figure 5.)
- the computer program is for example chosen within a library according to information relating to the hardware configuration of the electronic decoding device (information received by example during prior exchanges between the electronic encoding device 2 and the electronic decoding device).
- the control module 5 then proceeds to a step E16 of configuring the entropy coding.
- control module 5 determines a set of statistical sources with which to perform the entropy coding.
- the control module 5 determines for example a number of statistical sources (and therefore of contexts) to be used for the entropy coding.
- control module 5 can for example analyze the representative values V produced as indicated above and identify therein how many different statistical sources there are. According to another possibility, the control module 5 can choose the number of statistical sources according to the complexity that it wishes to authorize during the coding and/or the decoding.
- control module 5 can divide the signal formed by the set of representative values V into a certain number (for example less than or equal to a predetermined number, or, as a variant, without limiting their number) of sub-signals according to predefined criteria.
- control module 5 can create as many sub-signals as maps of characteristics F, or as many sub-signals as there are locations (i.e. distinct positions) in a map of characteristics F. Provision can optionally also be made for the control module 5 to be able to merge the sub-signals which have the same statistical distributions (or very similar statistical distributions).
- control module 5 also determines during the configuration step E16 with which statistical source (and therefore with which context) is associated each type of representative value V (that is to say here each element of a feature map).
- the command module 5 creates as many sub-signals as there are maps of characteristics F
- the context associated with an element of a map of characteristics F i.e. to be used to parameterize the entropy coding of this element depends on the F characteristic map concerned.
- control module 5 creates as many sub-signals as slots in each map of characteristics F, the context associated with an element of a map of characteristics F (that is to say to be used for set the entropy coding of this element) depends on the position of this element in the feature map F.
- the method of FIG. 3 then continues with steps of encoding data representative of the configuration of the entropy coder determined in step E16.
- the method of FIG. 3 firstly comprises a step E18 of coding a fourth header part comprising information 11 indicative of the set of contexts used for the entropy coding.
- information 11 is indicative of the number K of contexts used for the entropy coding.
- the method of FIG. 3 then comprises a step E20 of coding a fifth header part comprising, for each context used for the entropy coding, a linit data item for parameterizing the context concerned.
- the parameterization data linit associated with a given context is initialization data for this context, as described for example in Recommendation ITU-T H.265, part "9.3.2.2 Initialization process for context variables".
- the parametrization datum associated with a given context can be datum indicative of the probability model used for the context concerned during the entropy coding.
- the method of FIG. 3 then comprises a step E22 of coding a sixth header part comprising data 12 indicating, for each type of representative value V, the context in which the entropy coding of the representative values V having this type is realized.
- control module 5 selects as already indicated the assignment of the different contexts respectively to the different maps of characteristics F (each map of characteristics F forming a sub-signal), or respectively to the different positions (or locations) defined in the maps of features F (the elements having a given position forming a sub-signal).
- the data 12 include:
- an indicator I2_mode which indicates, if its value is 0, that a context is associated with each map of characteristics F and, if its value is 1, that a context is used for each position in the maps of characteristics F;
- the different types of representative values correspond to the different maps of characteristics F. If the I2_mode indicator is equal to 1, the different types of representative values correspond to the different positions within a map of characteristics F.
- control module 5 selects the assignment of the different contexts to the different characteristic maps, that is to say where the I2_mode indicator is equal to 0.
- the method of FIG. 3 continues with a step E24 of initialization of the entropic encoder 10 (by the control module 5) by means of the aforementioned parametrization data relating to the various contexts.
- This type of initialization is described in the document already mentioned (ITU-T Recommendation H.265, part "9.3.2.2 Initialization process for context variables").
- the method of FIG. 3 then comprises a step E26 of entropy coding of the representative values V by the entropy coder 10, the entropy coder 10 being parameterized at each instant (by the control module 5) in the context C used (according to the choices made as described above) for the type of the representative value V being processed.
- the control module 5 parameters the entropy coder 10 in the context C associated with this map of given characteristics F and successively applies (in a predefined order) the elements of this map of characteristics F at the input of the entropic encoder 10.
- the entropy coder 10 thus produces at output a sequence Fnn of binary elements representing, in compressed form, the audio or video content.
- the step E26 can include in some cases a sub-step (prior to the entropic coding strictly speaking) of binarization of the representative values V, as described in the article "Context-based adaptive binary arithmetic coding in the H.264/A VC video compression standard' cited above.
- the objective of this binarization step is to convert a representative value V which can take a large number of values into a series of binary elements, each binary element being coded by entropy coding (and in this case , a context is associated with the coding of each binary element).
- step E6 allows the processing of only part of the audio or video content to be compressed (for example when step E6 processes a block, or a component, or a image of a video sequence to be compressed), it is possible to repeat the implementation of steps E6 (to obtain values representative of the successive parts of the content) and E26 (to carry out the entropy coding of these representative values).
- the processor 4 can thus construct in step E28 the complete data stream comprising the header Fet and the sequence of bits Fnn.
- the complete data stream is constructed so that the Fet header and the Fnn sequence of bits are individually identifiable.
- the header Fet contains an indicator of the start of the sequence of bits Fnn in the complete data stream.
- This indicator is for example the location, in bits, of the beginning of the sequence of elements Fnn bits from the beginning of the complete data stream. (That is, the header in this case has a predetermined fixed length.)
- identifying the header Fet and the sequence of bits Fnn can be envisaged as a variant, such as for example a marker (i.e. a combination of bits used to indicate the start of the sequence of binary elements Fnn and whose use is prohibited in the rest of the data stream, or at least in the header Fet).
- a marker i.e. a combination of bits used to indicate the start of the sequence of binary elements Fnn and whose use is prohibited in the rest of the data stream, or at least in the header Fet.
- the data stream constructed in step E28 can be encapsulated in transmission formats known per se, such as the "Packet-Transport System” format or the "Byte-Stream” format.
- the data is coded by identifiable packets and transmitted over a communication network.
- the network can easily identify data boundaries (pictures, groups of pictures and here header Fet and sequence of bits Fnn), using the packet identification information provided by the network layer.
- step E28 In the "Byte-Stream" format, there are no specific packets and the construction of step E28 must make it possible to identify the boundaries of the relevant data (such as boundaries between parts of the stream corresponding to each image, and here between header Fet and sequence of bits Fnn) using additional means, such as the use of network abstraction layer units (or NAL units for “Network Abstraction Layer”), where unique combinations of bits (such as 0x00000001 ) are used to identify data boundaries).
- network abstraction layer units or NAL units for “Network Abstraction Layer”
- step E28 The complete data stream constructed in step E28 can then be sent in step E30 to the electronic decoding device 20 described below (by means of communication not shown and/or through at least one network of communication), or stored within the electronic coding device 2 (for subsequent transmission or, as a variant, subsequent decoding, for example within the electronic coding device itself, which is in this case designed to further implement the method decoding 20 described below with reference to Figure 5).
- This data stream thus comprises, as represented in FIG. 4, the header Fet and the sequence of bits Fnn.
- the Fet header includes: - a first part Fc which comprises data characteristic of the representation format of the audio or video content;
- I2 which comprises a plurality of identifiers I2_map[i] each representative of a context in which the entropy coder has been configured for the entropy coding of data of a certain type and consequently in which an entropy decoder is set to obtain data of this type when the entropy decoder receives as input part of the sequence of bits, as described below.
- FIG. 5 represents an electronic decoding device 20 including an entropy decoder 23.
- This electronic decoding device 20 comprises a reception unit 21, a processor 24 (for example a microprocessor) and a parallelized processing unit 26, for example a graphics processing unit (or GPU for "Graphical Processing Unit") or a unit tensor processing (or TPU for "Tensor Processing Unit”).
- a processor 24 for example a microprocessor
- a parallelized processing unit 26 for example a graphics processing unit (or GPU for "Graphical Processing Unit") or a unit tensor processing (or TPU for "Tensor Processing Unit”).
- the reception unit 21 is for example a communication circuit (such as a radiofrequency communication circuit) and makes it possible to receive data (and in particular here the data stream described above) from an external electronic device, such as than the electronic coding device 2, and to communicate these data to the processor 24 (to which the reception unit 21 is for example connected by a bus).
- a communication circuit such as a radiofrequency communication circuit
- the electronic decoding device 20 also comprises a storage unit 22, for example a memory (possibly a rewritable nonvolatile memory) or a hard disk.
- a storage unit 22 for example a memory (possibly a rewritable nonvolatile memory) or a hard disk.
- the storage unit 22 is shown in Figure 5 as a separate element of the processor 24, the storage unit 22 could alternatively be integrated with (i.e. included in) the processor 24.
- the processor 24 is in this case designed to successively execute a plurality of instructions of a computer program stored for example in the storage unit 22.
- control module 25 having in particular the functionalities described below.
- some of the functions of the control module 25 could be implemented due to the execution, by the processor 24, of instructions identified within the header Fet at step E52 as described below. below.
- Another part of the instructions stored in the storage unit 22 allow, when they are executed by the processor 24, to implement the entropy decoder 23 already mentioned.
- the entropy decoder 23 could be implemented due to the execution, by the processor 24, of instructions identified within the header Fet at step E52 as described below.
- the entropy decoder 23 is designed to perform an inverse entropy decoding of the entropy coding performed by the entropy encoder 10 of the electronic coding device 2 described above with reference to FIG.
- the entropy decoder 23 is therefore here a CABAC type entropy decoder (for "Context-based adaptive binary arithmetic coding").
- CABAC type entropy decoder for "Context-based adaptive binary arithmetic coding”
- it could be another type of entropy encoder, for example a Huffman type decoder, an arithmetic decoder or an LZW (for "Lempel-Ziv-Welch”) decoder.
- the parallelized processing unit 26 is designed to implement the artificial neural network 28 after having been configured by the processor 24 (here precisely by the control module 25). To do this, the processing unit parallelized 26 is designed to perform in parallel at a given time a plurality of operations of the same type.
- the parallelized processing unit 26 is designed to implement an automatic learning method (such as for example a deep learning method or a decision tree forest learning method) after having been configured by the processor 24, for example by means of configuration data of such an automatic learning method received within the data stream.
- an automatic learning method such as for example a deep learning method or a decision tree forest learning method
- the processor 24 receives (here via the reception unit 21) the data stream comprising the header Fet and the sequence of bits Fnn.
- the artificial neural network 28 is used within the framework of a processing of data obtained by entropic decoding of the sequence of binary elements Fnn, this processing of data aiming to obtain an audio or video content corresponding to the initial audio or video content B.
- the storage unit 22 can store a plurality of sets of parameters, each set of parameters defining a network of artificial decoding neurons.
- the processor 24 can in this case configure the parallelized processing unit 26 by means of a particular set of parameters among these sets of parameters so that the parallelized processing unit 26 can then implement the artificial neural network defined by this particular set of parameters.
- the storage unit 22 can in particular store a first set of parameters defining a first network of artificial neurons forming a random access decoder and/or a second set of parameters defining a second network of artificial neurons forming a low latency decoder.
- the electronic decoding device 20 in this case holds in advance decoding possibilities both for situations where it is desired to obtain random access to the content and for situations where it is desired to display the content without delay.
- the method of FIG. 6 begins a step E50 of reception (by the electronic decoding device 20, and precisely here by the reception unit 21) of the data stream comprising the header Fet and the sequence of binary elements Fnn.
- the receiving unit 21 transmits the received data stream to the processor 24 for processing by the control module 25.
- control module 25 then proceeds to a step E52 of identifying the header Fet and the sequence of bits Fnn within the data stream received, for example by means of the start of sequence indicator binary elements (already mentioned during the description of step E28).
- the control module 25 can also identify in step E52 the different parts of the header Fet (as described above with reference to FIG. 4).
- control module 25 can launch at step E54 the execution of these executable instructions in order to implement at least some of the steps (described below) for processing the header data (and possibly entropy decoding).
- These instructions can be executed by the processor 24 or, as a variant, by a virtual machine instantiated within the electronic decoding device 20.
- the method of FIG. 6 continues with a step E56 of decoding data Fc characteristic of the format for representing the audio or video content so as to obtain characteristics of this format.
- the decoding of the Fc data makes it possible to obtain the dimensions (in pixels) of the images and/or the frame rate and/or the bit depth of the luminance information and/or the bit depth of the chrominance information.
- the control module 25 then proceeds to a step E58 of decoding the data R indicative of the decoding artificial neural network to be used.
- these data R are an identifier designating the decoding artificial neural network 28, for example within a predetermined set of artificial neural networks.
- This predetermined set is for example the set of artificial neural decoding networks accessible by the electronic decoding device 20, namely the set of artificial neural networks for which the electronic decoding device 20 stores a set of parameters defining the artificial neural network concerned (as indicated above) or may have access to this set of parameters by connection to remote electronic equipment such as a server (as explained below).
- the control module 25 can in this case read, for example in the storage unit 22, a set of parameters associated with the decoded identifier (this set of parameters defining the artificial neural network identified by the 'decoded identifier).
- control module 25 can issue a request for a set of parameters intended for a remote server (this request including for example the decoded identifier) and receiving in response the set of parameters defining the artificial neural network identified by the decoded identifier.
- the data R are descriptive data Rc of the decoding artificial neural network 28.
- these descriptive data are for example coded in accordance with a standard such as the MPEG-7 part 17 standard or in a format such as the JSON format.
- decoding of these descriptive data makes it possible to obtain the parameters defining the artificial neural network to be used for the decoding of the data obtained (by entropy decoding) from the sequence of binary elements Fnn.
- the use of the aforementioned first possibility or the second possibility depends on an indicator also included in the R data, as already indicated.
- the decoding of the data R indicative of the decoding artificial neural network to be used makes it possible (here to the control module 25) to determine the characteristics of the decoding artificial neural network 28.
- the control module 25 thus determines the number N of feature maps expected at the input of the decoding artificial neural network 28 and the dimensions H, W of these feature maps.
- the input layer of the decoding artificial neural network 28 corresponding to the output layer of the coding artificial neural network 8 as explained above (see for example the description of step E2)
- each element d A feature map F is associated in a predetermined manner with an input node (or input layer node) of the decoding artificial neural network.
- the number and the dimensions of the maps of characteristics F are therefore linked to the characteristics of the decoding artificial neural network 28, as well as to certain header data such as the aforementioned data Fc (comprising in particular the dimensions of the image) .
- the control module 25 then proceeds in step E60 to configure the parallelized processing unit 26 by means of the parameters defining the decoding artificial neural network 28 (parameters obtained in step E58), or in general the automatic learning method used, so that the parallelized processing unit 26 can implement the decoding artificial neural network 28 (or in general the automatic learning method, for example as a variant another deep learning method or a decision tree forest learning process).
- This configuration step E60 includes in particular the instantiation of the decoding artificial neural network 28 within the parallelized processing unit 26, here by using the parameters obtained in step E58.
- This instantiation may include the following steps:
- the control module 25 then proceeds in step E64 to decoding the parameterization data Init relating respectively to the different contexts of the set of contexts used (this set being determined thanks to the information I1 decoded in step E62).
- the control module 25 can then implement a step E66 for initializing each usable context within the entropy decoder 23 by means of the parameterization data linit of the context concerned (decoded in step E64).
- each context is initialized with the probability model defined by the parametrization datum linit relating to this context.
- control module 25 configures in step E66 each context usable by the entropy decoder with the probability model defined by the parameterization datum linit relating to this context.
- the control module 25 then performs a step E68 of decoding the data I2 indicating, for each type of data to be obtained by entropy decoding, the context in which the entropy coding of the data having this type has been carried out and consequently in which the entropy decoder 23 must be configured for the entropy decoding of this data.
- control module 25 decodes (that is to say here consults) first of all the flag I2_mode which indicates, if its value is 0, that a context is associated with each card of features F and, if its value is 1 , that a context is used for each position in the maps of features F.
- the control module 25 decodes (i.e. here reads from the data stream) the identifiers I2_map[i] each representative of a context in which the entropy decoder 23 must be parameterized to obtain data of this type when the entropy decoder 23 receives as input part of the sequence of binary elements Fnn.
- the control module 25 decodes (or reads), for each of the N maps of characteristics F, the identifier I2_map[i] representing the context in which the entropy decoder 23 must be parameterized. to obtain the data (here the representative values V) relating to this map of characteristics F.
- the data here the representative values V
- the type of data is defined by the map of characteristics F to which this data belongs (this data here being a representative value V).
- the control module 25 decodes (or reads), for each of the WxH positions (or locations) within each map of characteristics F, the identifier I2_map[i] representative of the context in which the entropy decoder 23 must be parameterized to obtain the data (here the representative values V) located at this position.
- the type of a datum is defined by the position of this datum (here a representative value V) within the map of characteristics F concerned.
- step E70 the control module 25:
- the entropic decoder 23 applies at the input of the entropy decoder 23 a part of the sequence of binary elements Fnn (in the order of reception of these binary elements), so that the entropic decoder 23 produces at output the expected datum (here a representative value V ) identical to that which was coded by entropy coding in step E26.
- control module 25 has previously determined the number N and the dimensions H, W of the characteristic maps and therefore knows the number of representative values V (or expected data) to be obtained during the entropy decoding step E70. Moreover, as mentioned during the description of step E26, the various representative values V are coded by entropy coding in a predefined order and the representative values V (expected data) are therefore decoded in this same predefined order.
- the context C determined to decode an element (/.e. a representative value V) of a given feature map F is thus determined on the basis of the identifier I2_map[i] T1 associated with this given map of characteristics F (the type of data corresponding in this case to the map of characteristics comprising this data).
- the context C determined to decode a given element (/.e. a given representative value V) in a feature map F is determined on the basis of the identifier I2_map[i] associated with the position of this given element in the feature map (the data type corresponding in this case to the position of the data).
- the entropy decoder 23 thus produces in step E70 the sequence of expected data, namely here the set of representative values V.
- the processor 24 (here directly at the output of the entropy decoder 23 or, as a variant, via the control module 25) can then apply (/.e. present) in step E72 the representative values V to the neural network artificial 28 implemented by the parallelized processing unit 26 so that these data are processed by a decoding process using at least in part the artificial neural network 28.
- the artificial neural network 28 receives as input the representative values V and produces as output a representation I of the coded content suitable for reproduction on an audio or video reproduction device.
- the representative values V here in the form of feature maps F
- the output layer of the artificial neural network 28 produces the aforementioned representation I of the encoded content .
- the artificial neural network 28 thus produces as output (that is to say at the level of its output layer) at least one representation matrix I of an image.
- step E6 the association of an element (/.e. of a representative value V) of a map of characteristics F with an input node (or input layer node) is predefined.
- the artificial neural network 28 can receive as input at least some of the data produced at the output of the artificial neural network 28 during the processing of previous data (here representative values V previous), corresponding for example to the previous block or to the previous frame. In this case, a step E74 of reinjecting data produced at the output of the artificial neural network 28 into the input of the artificial neural network 28 is carried out.
- the decoding process could use a plurality of artificial neural networks, as already mentioned above with regard to the processing of content data B.
- the control module 25 determines in step E76 whether the processing of the sequence of binary elements Fnn by means of the artificial neural network 28 is finished. In the event of a negative determination (N), the method loops to step E70 for entropy decoding of the following part of the sequence of binary elements Fnn and application of other representative values V (produced by this entropy decoding) to the network of artificial neurons 28.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Compression, Expansion, Code Conversion, And Decoders (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| FR2009994A FR3114717B1 (fr) | 2020-09-30 | 2020-09-30 | Procédé et dispositif électronique de décodage d’un flux de données, programme d’ordinateur et flux de données associés |
| PCT/EP2021/076582 WO2022069437A1 (fr) | 2020-09-30 | 2021-09-28 | Procédé et dispositif électronique de décodage d'un flux de données, programme d'ordinateur et flux de données associés |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4222957A1 true EP4222957A1 (fr) | 2023-08-09 |
Family
ID=74045681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP21785841.4A Pending EP4222957A1 (fr) | 2020-09-30 | 2021-09-28 | Procédé et dispositif électronique de décodage d'un flux de données, programme d'ordinateur et flux de données associés |
Country Status (7)
| Country | Link |
|---|---|
| US (2) | US12483271B2 (fr) |
| EP (1) | EP4222957A1 (fr) |
| JP (1) | JP2023543480A (fr) |
| KR (1) | KR20230079143A (fr) |
| CN (1) | CN116601641A (fr) |
| FR (1) | FR3114717B1 (fr) |
| WO (1) | WO2022069437A1 (fr) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113810155B (zh) * | 2020-06-17 | 2022-11-18 | 华为技术有限公司 | 信道编译码方法和通信装置 |
| FR3114933B1 (fr) | 2020-10-06 | 2023-10-13 | Fond B Com | Procédé et dispositif électronique de décodage d’un flux de données, et programme d’ordinateur associé |
| FR3124342B1 (fr) * | 2021-06-17 | 2024-01-12 | Fond B Com | Procédés et dispositifs de décodage d’une partie au moins d’un flux de données, programme d’ordinateur et flux de données associés |
| US20250234005A1 (en) * | 2022-03-07 | 2025-07-17 | Lg Electronics Inc. | Feature encoding/decoding method, device, recording medium storing bitstream, and method for transmitting bitstream |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5548684A (en) * | 1994-04-22 | 1996-08-20 | Georgia Tech Research Corporation | Artificial neural network viterbi decoding system and method |
| FI107484B (fi) * | 1999-05-21 | 2001-08-15 | Nokia Mobile Phones Ltd | Menetelmä ja järjestely konvoluutiodekoodauksen toteuttamiseksi |
| US20040059992A1 (en) * | 2002-06-17 | 2004-03-25 | Tan Keng Tiong | Methods of optimizing the decoding of signals based on a complete majority logic representation |
| US9313514B2 (en) | 2010-10-01 | 2016-04-12 | Sharp Kabushiki Kaisha | Methods and systems for entropy coder initialization |
| HUE028417T2 (en) * | 2011-01-14 | 2016-12-28 | Ge Video Compression Llc | Entropy encoding and decoding scheme |
| US9215473B2 (en) * | 2011-01-26 | 2015-12-15 | Qualcomm Incorporated | Sub-slices in video coding |
| CN107529709B (zh) | 2011-06-16 | 2019-05-07 | Ge视频压缩有限责任公司 | 解码器、编码器、解码和编码视频的方法及存储介质 |
| JP6994868B2 (ja) | 2017-08-09 | 2022-01-14 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカ | 符号化装置、復号装置、符号化方法、および復号方法 |
| US10886943B2 (en) | 2019-03-18 | 2021-01-05 | Samsung Electronics Co., Ltd | Method and apparatus for variable rate compression with a conditional autoencoder |
| FR3112662B1 (fr) | 2020-07-17 | 2024-12-13 | Fond B Com | Procédé et dispositif électronique de décodage d’un flux de données, et flux de données associé |
| FR3112661B1 (fr) | 2020-07-17 | 2024-02-02 | Fond B Com | Procédés de décodage d’un flux de données, dispositifs et flux de données associés |
-
2020
- 2020-09-30 FR FR2009994A patent/FR3114717B1/fr active Active
-
2021
- 2021-09-28 EP EP21785841.4A patent/EP4222957A1/fr active Pending
- 2021-09-28 KR KR1020237014299A patent/KR20230079143A/ko active Pending
- 2021-09-28 JP JP2023519767A patent/JP2023543480A/ja active Pending
- 2021-09-28 WO PCT/EP2021/076582 patent/WO2022069437A1/fr not_active Ceased
- 2021-09-28 US US18/029,545 patent/US12483271B2/en active Active
- 2021-09-28 CN CN202180080189.8A patent/CN116601641A/zh active Pending
-
2025
- 2025-10-22 US US19/365,664 patent/US20260045958A1/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| CN116601641A (zh) | 2023-08-15 |
| JP2023543480A (ja) | 2023-10-16 |
| FR3114717A1 (fr) | 2022-04-01 |
| KR20230079143A (ko) | 2023-06-05 |
| US20260045958A1 (en) | 2026-02-12 |
| WO2022069437A1 (fr) | 2022-04-07 |
| FR3114717B1 (fr) | 2023-10-13 |
| US20230370087A1 (en) | 2023-11-16 |
| US12483271B2 (en) | 2025-11-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP4222957A1 (fr) | Procédé et dispositif électronique de décodage d'un flux de données, programme d'ordinateur et flux de données associés | |
| EP4183130B1 (fr) | Decodage video utilisant un reseau de neurones | |
| FR2974474A1 (fr) | Procedes et appareils de production et de traitement de representations de scenes multimedias | |
| EP4183133A1 (fr) | Decodage video parallelise utilisant un reseau de neurones | |
| WO2024121109A1 (fr) | Procédé et dispositif de codage et décodage d'images | |
| US20260019650A1 (en) | Electronic method and device for decoding a data stream, and associated computer program | |
| EP2368367A1 (fr) | Système et procédé interactif pour la transmission sur un réseau bas débit d'images clefs sélectionnées dans un flux video | |
| EP3826304A2 (fr) | Procédé et dispositif de compression d'images numériques et procédé et dispositif de décompression associés | |
| WO2017129880A1 (fr) | Procédé de codage et décodage de données, dispositif de codage et décodage de données et programmes d'ordinateur correspondants | |
| WO2024240496A1 (fr) | Procédé et dispositif de codage et décodage d'images | |
| EP4356606A1 (fr) | Procédés et dispositifs de décodage d'une partie au moins d'un flux de données, programme d'ordinateur et flux de données associés | |
| WO2018073523A1 (fr) | Procédé de codage et de décodage de paramètres d'image, dispositif de codage et de décodage de paramètres d'image et programmes d'ordinateur correspondants | |
| WO2024260629A1 (fr) | Procédé et dispositif de codage et décodage de séquences d'images | |
| EP4732241A1 (fr) | Procédé et dispositif de codage et décodage de séquences d'images | |
| FR3143246A1 (fr) | Procédé et dispositif de codage et décodage d’images. | |
| EP4630971A1 (fr) | Procédé et dispositif de codage et décodage d'images | |
| FR3143247A1 (fr) | Procédé et dispositif de codage et décodage de séquences d’images. | |
| WO2024240497A1 (fr) | Procédé et dispositif de codage et décodage d'images. | |
| WO2026003294A1 (fr) | Procédé et dispositif de codage et décodage d'un signal | |
| FR3114716A1 (fr) | Codage et décodage d’une vidéo multi-vues |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20230323 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: ORANGE |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20251007 |