-
公开(公告)号:EP4354874A1
公开(公告)日:2024-04-17
申请号:EP22853408.7
申请日:2022-08-02
发明人: DINH, Quockhanh , CHOI, Kwangpyo , PARK, Minwoo , PIAO, Yinji
IPC分类号: H04N19/86 , H04N19/176 , H04N19/82 , G06T9/00 , G06N3/04 , H04N19/117 , H04N19/147 , H04N19/159
CPC分类号: G06N3/04 , G06T9/00 , H04N19/117 , H04N19/147 , H04N19/159 , H04N19/176 , H04N19/82 , H04N19/86
摘要: An image processing method and an image processing apparatus are provided to obtain input data for deblocking filtering based on deblocking filtering target pixels of at least one line perpendicular to a boundary line of blocks and encoding information about the deblocking filtering target pixels of at least one line, obtain a feature map of the input data by inputting the input data to a first neural network, obtain a deblocking filter coefficient by inputting the feature map to a second neural network, obtain a deblocking filter compensation value by inputting the feature map to a third neural network, obtain a deblocking filter strength by inputting the input data to a fourth neural network, obtain deblocking filtered pixels by performing deblocking filtering on the deblocking filtering target pixels of the at least one line using the deblocking filter coefficient, the deblocking filter compensation value, and the deblocking filter strength.
-
32.
公开(公告)号:EP4354083A1
公开(公告)日:2024-04-17
申请号:EP23202390.3
申请日:2023-10-09
发明人: Günther, Martin , Müller, Nikolas
摘要: Die Erfindung betrifft ein Verfahren und eine Anordnung, um automatisch einen Raumplan einer Etage eines Gebäudes zu generieren. Eine Menge von Voxeln in Form von Polyedern wird rechnerisch erzeugt und füllt zusammen die Ebene aus. Die Kanten des Polyeders sind parallel zu den Achsen eines vorgegebenen dreidimensionalen Koordinatensystems. Eine Kamera (IR) wird durch die Etage bewegt und erzeugt eine Abfolge von Bildern. Die jeweilige Position und Orientierung der Kamera (IR) beim Erzeugen eines Bilds werden gemessen. Charakteristische Schlüsselpunkte (S1', S2',...) werden ermittelt und im Koordinatensystem positioniert. Freie Voxel (Vx, Vy), also Voxel im Inneren eines Raums, werden ermittelt. Mindestens ein Cluster, bestehend aus einer topologisch zusammenhängenden Menge von freien Voxeln, wird generiert. Um jeden ermittelten Cluster herum wird ein umhüllender Körper gelegt. Jeder umhüllende Körper beschreibt jeweils die Begrenzungen (W, F) eines Raums (R.x) der Etage.
-
公开(公告)号:EP3821373B1
公开(公告)日:2024-04-17
申请号:EP19833078.9
申请日:2019-07-08
IPC分类号: G06N3/02 , H04N19/503 , G06T9/00 , H04N19/172 , H04N19/132
CPC分类号: H04N19/103 , H04N19/154 , H04N19/172 , H04N19/147 , G06N3/084 , G06N3/044 , G06N3/045
-
34.
公开(公告)号:EP4340366A1
公开(公告)日:2024-03-20
申请号:EP23197252.2
申请日:2023-09-13
申请人: LIV, Inc.
发明人: Stehlik, Jaroslav , Perry, Alexander Brook , Brainville, Arthur Louis , Donal, Steffan Robert William , Adrian-Nicolae, Bunta , Ali Mudhir, Omar Mohamed , Shewki, Ajinyad Karwan
IPC分类号: H04N19/597 , G06T9/00 , H04N13/243 , H04N13/271 , H04N13/275 , H04N13/279
摘要: A system, method, and device are provided for creating a data processing pipeline to capture, transport, and interactively display in both recorded and real time any 3D volumetric simulation that was generated by a separate application. The system, method, and device enabling the interactive viewing of virtual and mixed reality simulations by a plurality of users.
-
公开(公告)号:EP4329312A1
公开(公告)日:2024-02-28
申请号:EP22819566.5
申请日:2022-06-08
发明人: ZHANG, Wei , NIE, Jiaming , LV, Zhuoyi , YANG, Fuzheng
摘要: This application discloses a point cloud encoding processing method and decoding processing method, and related devices. The point cloud encoding processing method of embodiments of this application includes: obtaining a current to-be-encoded node in a target queue, where the target queue includes an occupied node in a space block corresponding to a constructed tree structure based on first geometric information, the first geometric information is obtained by preprocessing based on geometric information of a to-be-encoded N-th frame point cloud, and N is an integer greater than 1; and determining an encoding mode of the current to-be-encoded node based on whether the current to-be-encoded node meets an encoding condition of an isolated point. The encoding condition of the isolated point includes: An occupancy status of a target node meets a preset condition. The target node is a node that is in encoded nodes and that is associated with the current to-be-encoded node.
-
公开(公告)号:EP4329310A1
公开(公告)日:2024-02-28
申请号:EP22791848.9
申请日:2022-01-26
申请人: LG Electronics Inc.
发明人: HUR, Hyejung
IPC分类号: H04N19/96 , H04N19/119 , H04N19/597 , H04N19/172 , G06T9/40
摘要: Disclosed herein is a method of transmitting point cloud data, including encoding point cloud data, and transmitting a bitstream containing the point cloud data. Disclosed herein a method of receiving point cloud data, including receiving a bitstream containing point cloud data, and decoding the point cloud data.
-
37.
公开(公告)号:EP4300959A1
公开(公告)日:2024-01-03
申请号:EP22212075.0
申请日:2022-12-07
IPC分类号: H04N19/172 , H04N19/114 , G06T9/00
摘要: The present disclosure provides video frame processing method and apparatus, model training method and apparatus, a device and a storage medium, relates to a field of artificial intelligence, and in particular, to cloud computing, video processing, and medium cloud technology, and may be applied in an intelligent cloud scenario. The video frame processing method includes: acquiring (S101) a target characteristic corresponding to a current video frame in a video frame sequence to be encoded, in the case of the video frame sequence to be encoded satisfies a preset condition; inputting (S102) the target characteristic corresponding to the current video frame to a first target model, to obtain a first output result corresponding to the current video frame; and determining (S103) a first target group of pictures, GOP, length corresponding to the current video frame, based on the first output result corresponding to the current video frame.
-
公开(公告)号:EP4290461A1
公开(公告)日:2023-12-13
申请号:EP23175291.6
申请日:2023-05-25
发明人: FENNEY, Simon , OZKAN, Alper
摘要: A method and a compression unit are provided for compressing, into a block of compressed data, a block of sub-primitive presence indications for use in a rendering system. The block of sub-primitive presence indications is subdivided into a plurality of parent regions, each of the parent regions being subdivided into a plurality of child regions. A presence state is identified for each of the child regions based on the sub-primitive presence indications in the block of sub-primitive presence indications. A hierarchical representation of the block of sub-primitive presence indications is stored in the block of compressed data. For each of one or more parent regions whose child regions all have the same identified presence state, parent-level data is included in the hierarchical representation to represent the presence state of the parent region without child-level data for the child regions within the parent region being included in the hierarchical representation. For each of one or more parent regions whose child regions do not all have the same identified presence state, child-level data for the child regions within the parent region is included in the hierarchical representation to represent the presence states for the child regions within the parent region.
-
39.
公开(公告)号:EP4287126A1
公开(公告)日:2023-12-06
申请号:EP23175288.2
申请日:2023-05-25
发明人: FENNEY, Simon , OZKAN, Alper
摘要: A method and a decompression unit are provided for decompressing compressed data to determine one or more sub-primitive presence indications for use in a rendering system. A block of compressed data is received for a block of sub-primitive presence indications. The block of sub-primitive presence indications is subdivided into a plurality of parent regions, each of the parent regions being subdivided into a plurality of child regions. The block of compressed data comprises a hierarchical representation of the block of sub-primitive presence indications, wherein: (i) for each of one or more parent regions whose child regions all have the same presence state, parent-level data is included in the hierarchical representation to represent the presence state of the parent region without child-level data for the child regions within the parent region being included in the hierarchical representation, and (ii) for each of one or more parent regions whose child regions do not all have the same presence state, child-level data for the child regions within the parent region is included in the hierarchical representation to represent the presence states for the child regions within the parent region. It is determined whether child-level data is included in the hierarchical representation for one of the parent regions. If it is determined that child-level data is included in the hierarchical representation for said one of the parent regions, child-level data for said one of the parent regions is used to determine one or more sub-primitive presence indications in said one of the parent regions. If it is determined that child-level data is not included in the hierarchical representation for said one of the parent regions, parent-level data for said one of the parent regions is used, without child-level data, to determine one or more sub-primitive presence indications in said one of the parent regions.
-
40.
公开(公告)号:EP4287125A1
公开(公告)日:2023-12-06
申请号:EP23175286.6
申请日:2023-05-25
发明人: OZKAN, Alper , FENNEY, Simon
摘要: A method and a compression unit are provided for compressing, into a block of compressed data, a block of sub-primitive presence indications for use in intersection testing in a rendering system. An ordered set of patches is obtained which represents the presence indications in the block of sub-primitive presence indications. At least two of the patches in the set of patches partially overlap with each other. Data defining the patches of the set of patches is stored in the block of compressed data. The data defining each of the patches defines a presence state of the patch and a position of the patch within the block of sub-primitive presence indications.
-
-
-
-
-
-
-
-
-