-
1.
公开(公告)号:WO2023046500A1
公开(公告)日:2023-03-30
申请号:PCT/EP2022/075043
申请日:2022-09-08
Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS
Inventor: LAMBERT, Anne , OZEROV, Alexey , FONTAINE, Patrick
Abstract: A method or apparatus that combines properties of parallel distribution and flexibility of distribution of convolutional neural networks on heterogeneous devices uses parallelization for distributed inference of Deep Neural Networks. The method addresses parallel distribution among various numbers of devices of various capacities. A network is distributed in parallel for each configuration and is adaptive to different network capabilities.
-
2.
公开(公告)号:WO2023012073A1
公开(公告)日:2023-02-09
申请号:PCT/EP2022/071451
申请日:2022-07-29
Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS
Inventor: LE GUYADEC, Pascal , QUINQUIS, Cyril , FILOCHE, Thierry , ONNO, Stephane
Abstract: Procedures, methods, architectures, apparatuses, systems, devices, and computer program products of machine learning using a first machine learning (ML) module implementing a first ML model and a second ML module implementing a second ML model, the method comprising: receiving, by the second ML module, first prediction results of the first ML model, the first prediction results being based on input data; generating, by the second ML module, second prediction results using the second ML model based on the input data; determining, by the second ML module, an accuracy metric based on a comparison of the first prediction results of the first ML model and the second prediction results of the second ML model; and sending, by the second ML module, the determined accuracy metric and an accuracy condition.
-
公开(公告)号:WO2023285336A1
公开(公告)日:2023-01-19
申请号:PCT/EP2022/069227
申请日:2022-07-11
Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS
Inventor: MARQUANT, Gwenaelle , MORIN, Thomas
IPC: G06F16/955
Abstract: A user may download on his/her device, a webpage from a webserver, using the webpage resource identifier. The user may add an annotation, e.g., may add highlight, emphasis, and/or comments, to an item of the webpage, i.e., an annotation target. The Document Object Model, DOM, structure of the webpage source code may be parsed to search for a set of elements, e.g. HTML or XML elements, that identify a location of the annotation target in the webpage source code. The set of elements thus found, may be encoded in an extension to the webpage resource identifier, and the webpage with the extension may be transmitted to another device of another user. At the other device, the webpage may be downloaded from the webserver using the resource identifier, and the other device may render the annotation, as encoded in the extension.
-
4.
公开(公告)号:WO2023274792A1
公开(公告)日:2023-01-05
申请号:PCT/EP2022/066914
申请日:2022-06-21
Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS
Inventor: HASKOU, Abdullah , LOUZIR, Ali , PESIN, Anthony
Abstract: A signature of an activity may be obtained based on a radar processing of a signal that may be obtained in presence of a user performing the activity e.g., in the range of a radar transceiver. For example, the obtained signature of the activity may be divided in a set of sub-signatures of the activity according to a set of intervals of intensity (e.g., values). For example, reference signatures of the activities of the set of activities may be divided in reference sub signatures according to the same set of intervals of intensity. For example, the activity may be recognized by correlating the different sub signatures of the obtained signature to different reference sub signatures according to the set of intervals of intensity.
-
公开(公告)号:WO2022268748A1
公开(公告)日:2022-12-29
申请号:PCT/EP2022/066783
申请日:2022-06-21
Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS
Inventor: STAUDER, Jurgen , MORVAN, Patrick , ORHAND, Anita
IPC: H04N1/60 , H04N1/6019
Abstract: A device applies a pre-function to an input signal to obtain an intermediate signal, wherein the pre-function has a linear section part of the input range. The device then applies a LUT including LUT entries that define a linear section and that delimit the range of the intermediate signal that corresponds to the part of the input range, resulting in an output signal that can be linearly processed through the pre-function and the LUT. The device can process a signal with positive and negative values, where one of these lies in the part of the input range that results in linear processing.
-
公开(公告)号:WO2022233763A1
公开(公告)日:2022-11-10
申请号:PCT/EP2022/061660
申请日:2022-05-02
Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS
Inventor: DOYEN, Didier , DRAZIC, Valter , BRAC DE LA PERRIERE, Vincent , BOISSON, Guillaume
IPC: H04N19/597 , G03H1/08 , H04N19/70
Abstract: Methods and apparatuses for encoding/decoding data content representative of a volumetric video are provided, wherein, the encoding/decoding comprises encoding in/decoding from a bitstream, an indicator specifying whether data content has information representative of at least one set of depth layers, the information representative of a set of depth layers specifying a number of depth layers and a depth value for each of the depth layers for a layer-based representation of the volumetric video. Methods and apparatuses for reconstructing Computer Generated Holograms from a reconstructed layered-based representation of the volumetric video are also provided.
-
公开(公告)号:WO2022214435A1
公开(公告)日:2022-10-13
申请号:PCT/EP2022/058896
申请日:2022-04-04
Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS
Inventor: CHUPEAU, Bertrand , DORE, Renaud , FLEUREAU, Julien , THUDOR, Franck
IPC: G06T17/00 , H04N19/597 , G06T9/00
Abstract: Methods, devices and data streams are proposed to encode, transport and decode 3D volumetric videos. The embodiments encompass the signaling of non-Lambertian patches together with their light reflection properties, so as to enable a ray-tracing based rendering engine to synthesize visually realistic virtual views with respect to light effects. A retro-compatible solution enabling conventional rendering engines to render such described 3D scene but without the advanced light effects is also described.
-
公开(公告)号:WO2022079008A1
公开(公告)日:2022-04-21
申请号:PCT/EP2021/078148
申请日:2021-10-12
Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS
Inventor: ANDRIVON, Pierre , GUEDE, Celine , RICARD, Julien , MARVIE, Jean-Eudes
Abstract: A method and device are provided for rendering an image. The method comprises receiving an image from at least two different camera positions and determining a camera orientation and at least one image attribute associated with each of the positions. A model is then generated of the image based on the attribute and camera orientation associated with the received camera positions of the image. The model is enabled to provide a virtual rendering of the image at a plurality viewing orientations and selectively providing appropriate attributes associated with the viewing orientation.
-
公开(公告)号:WO2022073796A1
公开(公告)日:2022-04-14
申请号:PCT/EP2021/076558
申请日:2021-09-28
Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS
Inventor: HOUDAILLE, Rémi , SALMON-LEGAGNEUR, Charles , TAIBI, Charline , TRAVERT, Serge
IPC: H04N21/81 , H04N21/854 , H04N21/234 , H04N21/44 , H04N21/414 , H04N21/4728 , H04N21/2662 , H04N19/119 , H04N19/167 , H04N19/70
Abstract: Methods and devices are disclosed to adapt a full-resolution 360° volumetric video content to the processing resources of different client devices. A 3D scene or a sequence of 3D scenes encoded as patch pictures, for example packed in atlas images is obtained; Patch pictures of the atlases are organized according to a sectorization of the three-dimensional space. Then, a request comprising information representative of a pose is received from a client device. Sectors of the sectorization are selected as a function of the pose information and the sectorization. The corresponding part is extracted and/or recomposed, encoded and transmitted to the client device.
-
10.
公开(公告)号:WO2022069522A1
公开(公告)日:2022-04-07
申请号:PCT/EP2021/076755
申请日:2021-09-29
Applicant: INTERDIGITAL CE PATENT HOLDINGS, SAS
Inventor: CHUPEAU, Bertrand , THUDOR, Franck , DORE, Renaud
IPC: H04N19/597 , H04N19/70
Abstract: Methods, apparatus and data stream are described to encode, transmit and decode an atlas- based representation of a 3D scene based on a multiplane image (MPI) representation in which a depth component is encoded in each layer. Layers of the MPI are clustered on a transparency basis to generate texture, transparency and depth patch pictures. Patch pictures are packed in at least one atlas image. Metadata associating each patch to a layer and each layer to a depth and a depth quantization law are encoded in the data stream with the at least one atlas. At the decoding side, the MPI with a depth component is retrieved from the data stream and is used to render a viewport image from a viewpoint in the neighborhood of the center of the MPI.
-
-
-
-
-
-
-
-
-