公开(公告)号：US20160007005A1

公开(公告)日：2016-01-07

申请号：US14852288

申请日：2015-09-11

Applicant: Huawei Technologies Co., Ltd.

Inventor： Jacek KONIECZNY ,  Fabian JAEGER ,  Mathias WIEN

IPC: H04N13/00 ,  H04N19/70 ,  H04N19/157 ,  H04N19/136

CPC classification number: H04N13/161 ,  H04N19/136 ,  H04N19/157 ,  H04N19/463 ,  H04N19/48 ,  H04N19/597 ,  H04N19/70 ,  H04N2013/0081 ,  H04N2213/005

Abstract: The invention relates to a method (200) for sub-range based coding a depth lookup table (300), the depth lookup table comprising depth values of a 3D video sequence, the depth values being constrained within a range (301), the method comprising: partitioning (201) the range (301) into a plurality of sub-ranges, a first sub-range (303) comprising a first set of the depth values and a second sub-range (305) comprising a second set of the depth values; and coding (203) the depth values of each of the sub-ranges of the depth lookup table (300) separately according to a predetermined coding rule.

Abstract translation: 本发明涉及一种用于基于子范围的编码深度查找表（300）的方法（200），深度查找表包括3D视频序列的深度值，深度值被限制在一个范围内（301），该方法 包括：将所述范围（301）划分（201）为多个子范围，包括所述深度值的第一组的第一子范围（303）和包括所述深度值的第二组的第二子范围（305） 深度值 以及根据预定的编码规则分别对深度查找表（300）的每个子范围的深度值进行编码（203）。

公开(公告)号：US20160345007A1

公开(公告)日：2016-11-24

申请号：US15194197

申请日：2016-06-27

Applicant: Huawei Technologies Co., Ltd.

Inventor： Fabian JAEGER ,  Jacek KONIECZNY

IPC: H04N19/115 ,  H04N19/119 ,  H04N19/182 ,  H04N19/176 ,  H04N19/50

CPC classification number: H04N19/115 ,  G06T9/20 ,  H04N19/119 ,  H04N19/136 ,  H04N19/176 ,  H04N19/182 ,  H04N19/21 ,  H04N19/50 ,  H04N19/597

Abstract: Embodiments of the invention relates to an apparatus for associating a video block partitioning pattern to a video coding block, wherein the apparatus comprises: an obtainer adapted to obtain values of a set of segmentation mask samples, wherein each segmentation sample of the set of segmentation mask samples represents a different position in a segmentation mask adapted to define video coding block partitions of the video coding block; a selector adapted to select a video block partitioning pattern from a predetermined group of video block partitioning patterns based on the values of segmentation mask samples of the set of segmentation mask samples; andan associator adapted to associate the selected video block partitioning pattern to the video coding block.

Abstract translation: 适合于将所选择的视频块分割模式与视频编码块相关联的关联器。

公开(公告)号：US20200019860A1

公开(公告)日：2020-01-16

申请号：US16579665

申请日：2019-09-23

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Jacek KONIECZNY

IPC: G06N3/08 ,  G06N3/04

Abstract: Embodiments of the invention relates to a data processing apparatus comprising a processor configured to provide a neural network, wherein the neural network comprises a neural network layer being configured to generate from an array of input data values an array of output data values based on a plurality of position dependent kernels and a plurality of input data values of the array of input data values. Moreover, embodiments of the invention relates to a corresponding data processing method.

公开(公告)号：US20180182119A1

公开(公告)日：2018-06-28

申请号：US15860930

申请日：2018-01-03

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Jacek KONIECZNY ,  Marek DOMANSKI ,  Jakub SIAST ,  Adam LUCZAK ,  Olgierd STANKIEWICZ ,  Krzysztof WEGNER

IPC: G06T7/593

CPC classification number: G06T7/593 ,  G06T7/55 ,  G06T2200/28 ,  G06T2207/10012 ,  G06T2207/10028

Abstract: The disclosure relates to an image processing apparatus for selecting a plurality of depth information values for a subset of currently processed fragments of a set of currently processed fragments of a currently processed digital image. The image processing apparatus includes a non-transitory memory storage comprising instructions and one or more hardware processors in communication with the memory storage. The one or more hardware processors execute the instructions to: process the currently processed fragments of the set of currently processed fragments in parallel; and process the currently processed fragments of the subset of currently processed fragments in parallel.

公开(公告)号：US20180144491A1

公开(公告)日：2018-05-24

申请号：US15860662

申请日：2018-01-03

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Jacek KONIECZNY ,  Marek Domanski ,  Olgierd Stankiewicz ,  Krzysztof Wegner ,  Adam Luczak

IPC: G06T7/55

CPC classification number: G06T7/55 ,  G06T2207/10012 ,  G06T2207/10028 ,  G06T2207/20228

Abstract: The present disclosure can provide an image processing apparatus. In some embodiments, the image processing apparatus in accordance with the disclosure comprises memory configured to store a previously selected depth information value (dprev), (dprev; dprevi) having been selected for a previously processed fragment and signal processing logic (103). The signal processing logic is configured to calculate a similarity measure for the current fragment based on a depth information value candidate defining a reference fragment candidate of a digital reference image, compare the depth information value candidate with the previously selected depth information value (dprev), apply a weighting function to the calculated similarity measure to obtain a weighted similarity measure for the current fragment based on the comparison, and determine whether to select the depth information value candidate as the depth information value (dbest) for the current fragment based on the weighted similarity measure of the depth information value candidate.