# US 12,113,963 B2 · Method and apparatus for selecting neighbor point in point cloud, encoder, and decoder > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,113,963 B2 - Document ID: US12113963B2 - Status: Granted - Kind: B2 - Application number: 17/978,116 - Filed: 2022-10-31 - Published: 2023-02-16 - Granted: 2024-10-08 - Earliest claimed: 2021-03-12 - Assignees: Tencent Technology (Shenzhen) Company Limited - Applicants: Tencent Technology (Shenzhen) Company Limited - Inventors: Wenjie Zhu - Web page: https://patentgrep.com/patent/US12113963B2 ## CPC - G06T 9/001: {Model-based coding, e.g. wire frame} - H04N 19/105: Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction - H04N 19/119: Adaptive subdivision aspects, e.g. subdivision of a picture into rectangular or non-rectangular coding blocks - H04N 19/167: Position within a video image, e.g. region of interest [ROI] - H04N 19/597: specially adapted for multi-view video sequence encoding - H04N 21/2343: involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements {(video transcoding H04N19/40; media packet handling at the source H04L65/762)} - H04N 21/4402: involving reformatting operations of video signals for household redistribution, storage or real-time display {(details of conversion of video standards at pixel level H04N7/01; video transcoding H04N19/40; adapting incoming signals to the display format of the display terminal G09G5/005; media handling at the source in data packet switching networks H04L65/764)} - Y02D 30/70: in wireless communication networks - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE ## Abstract This application provides a method for selecting a neighbor point of a current point in a point cloud. The method includes: determining, from point cloud data, a target region where the current point is located, the target region comprising a plurality of points; determining, for at least two decoded target points in the target region, a weight coefficient of each of the at least two target points, the at least two target points not comprising the current point; determining a weight of each of the at least two target points according to the weight coefficient and geometry information of each of the at least two target points and geometry information of the current point; and selecting at least one from the at least two target points according to the weight of each of the at least two target points as the neighbor point of the current point. ## Claims ### Claim 1 A method for selecting a neighbor point of a current point in a point cloud performed by a computer device, the method comprising: determining, from point cloud data, a target region where the current point is located, the target region comprising a plurality of points; determining, for at least two decoded target points in the target region, a weight coefficient of each of the at least two target points, the at least two target points not comprising the current point, wherein the weight coefficient is a preset fixed value; determining a weight of each of the at least two target points according to the weight coefficient and a distance between each of the at least two target points and the current point according to geometry information of each of the at least two target points and geometry information of the current point; and selecting at least one from the at least two target points according to the weight of each of the at least two target points as the neighbor point of the current point. ### Claim 2 (depends on 1) The method according to claim 1, wherein the determining a weight coefficient of each of the at least two target points comprises: obtaining the weight coefficient of each of the at least two target points by decoding a code stream corresponding to the point cloud data; or, dividing the at least two target points into at least one group, and determining a default weight coefficient corresponding to each of the at least one group as the weight coefficient of each point in each group; or, determining the weight coefficient of each of the at least two target points according to the geometry information of each of the at least two target points; or, determining the weight coefficient of each of the at least two target points according to attribute information of each of the at least two target points. ### Claim 3 (depends on 2) The method according to claim 2, wherein the weight coefficient comprises a weight coefficient of a first component, a weight coefficient of a second component, and a weight coefficient of a third component; the weight coefficient of the first component, the weight coefficient of the second component, and the weight coefficient of the third component corresponding to the same group in the at least one group are all equal; or, at least two coefficients from among the weight coefficient of the first component, the weight coefficient of the second component, and the weight coefficient of the third component corresponding to the same group in the at least one group are unequal. ### Claim 4 (depends on 2) The method according to claim 2, wherein the weight coefficient comprises a weight coefficient of a first component, a weight coefficient of a second component, and a weight coefficient of a third component; and the determining the weight coefficient of each of the at least two target points according to the geometry information of each of the at least two target points comprises: determining a first distribution value of the at least two target points in a first component direction, a second distribution value of the at least two target points in a second component direction, and a third distribution value of the at least two target points in a third component direction respectively according to the geometry information of each of the at least two target points; and determining the weight coefficient of each of the at least two target points according to the first distribution value, the second distribution value, and the third distribution value. ### Claim 5 (depends on 4) The method according to claim 4, wherein the determining a first distribution value of the at least two target points in a first component direction, a second distribution value of the at least two target points in a second component direction, and a third distribution value of the at least two target points in a third component direction respectively according to the geometry information of each of the at least two target points comprises: determining a first value range of the at least two target points in the first component direction according to the geometry information of each of the at least two target points in the first component direction; determining a second value range of the at least two target points in the second component direction according to the geometry information of each of the at least two target points in the second component direction; determining a third value range of the at least two target points in the third component direction according to the geometry information of each of the at least two target points in the third component direction; and determining the first distribution value, the second distribution value, and the third distribution value according to the first value range, the second value range, and the third value range. ### Claim 6 (depends on 5) The method according to claim 5, wherein the determining the first distribution value, the second distribution value, and the third distribution value according to the first value range, the second value range, and the third value range comprises: determining a range value of the first value range as the first distribution value; determining a range value of the second value range as the second distribution value; and determining a range value of the third value range as the third distribution value. ### Claim 7 (depends on 5) The method according to claim 5, wherein the determining the first distribution value, the second distribution value, and the third distribution value according to the first value range, the second value range, and the third value range comprises: determining a first ratio of the number of the at least two target points to the range value of the first value range, and determining the first ratio as the first distribution value; determining a second ratio of the number of the at least two target points to the range value of the second value range, and determining the second ratio as the second distribution value; and determining a third ratio of the number of the at least two target points to the range value of the third value range, and determining the third ratio as the third distribution value. ### Claim 8 (depends on 4) The method according to claim 4, wherein the determining a first distribution value of the at least two target points in a first component direction, a second distribution value of the at least two target points in a second component direction, and a third distribution value of the at least two target points in a third component direction respectively according to the geometry information of each of the at least two target points comprises: determining a first variance of the at least two target points in the first component direction according to the geometry information of each of the at least two target points in the first component direction; determining a second variance of the at least two target points in the second component direction according to the geometry information of each of the at least two target points in the second component direction; determining a third variance of the at least two target points in the third component direction according to the geometry information of each of the at least two target points in the third component direction; and determining the first distribution value, the second distribution value, and the third distribution value according to the first variance, the second variance, and the third variance. ### Claim 9 (depends on 2) The method according to claim 2, wherein the weight coefficient comprises a weight coefficient of a first component, a weight coefficient of a second component, and a weight coefficient of a third component; and the determining the weight coefficient of each of the at least two target points according to attribute information of each of the at least two target points comprises: determining, according to the geometry information of each of the at least two target points, a center point of a region enclosed by the at least two target points; determining, respectively from among the at least two target points, a first point that is farthest to the center point in the first component direction, a second point that is farthest to the center point in the second component direction, and a third point that is farthest to the center point in the third component direction; determining the first distribution value of the at least two target points in the first component direction, the second distribution value of the at least two target points in the second component direction, and the third distribution value of the at least two target points in the third component direction respectively according to the attribute information of each of the first point, the second point, and the third point; and determining the weight coefficient of each of the at least two target points according to the first distribution value, the second distribution value, and the third distribution value. ### Claim 10 (depends on 4) The method according to claim 4, wherein the determining the weight coefficient of each of the at least two target points according to the first distribution value, the second distribution value, and the third distribution value comprises: determining the first distribution value as the weight coefficient of the first component, determining the second distribution value as the weight coefficient of the second component, and determining the third distribution value as the weight coefficient of the third component; or, determining a sum of the first distribution value, the second distribution value, and the third distribution value, determining, according to a ratio of the first distribution value to the sum, the weight coefficient of the first component, determining, according to a ratio of the second distribution value to the sum, the weight coefficient of the second component, and determining, according to a ratio of the third distribution value to the sum, the weight coefficient of the third component. ### Claim 11 A computing device, comprising a processor and a memory, wherein the memory being configured to store computer-readable instructions; and the processor being configured to execute the computer-readable instructions to implement a method for selecting a neighbor point of a current point in a point cloud including: determining, from point cloud data, a target region where the current point is located, the target region comprising a plurality of points; determining, for at least two decoded target points in the target region, a weight coefficient of each of the at least two target points, the at least two target points not comprising the current point, wherein the weight coefficient is a preset fixed value; determining a weight of each of the at least two target points according to the weight coefficient and a distance between each of the at least two target points and the current point according to geometry information of each of the at least two target points and geometry information of the current point; and selecting at least one from the at least two target points according to the weight of each of the at least two target points as the neighbor point of the current point. ### Claim 12 (depends on 11) The computing device according to claim 11, wherein the determining a weight coefficient of each of the at least two target points comprises: obtaining the weight coefficient of each of the at least two target points by decoding a code stream corresponding to the point cloud data; or, dividing the at least two target points into at least one group, and determining a default weight coefficient corresponding to each of the at least one group as the weight coefficient of each point in each group; or, determining the weight coefficient of each of the at least two target points according to the geometry information of each of the at least two target points; or, determining the weight coefficient of each of the at least two target points according to attribute information of each of the at least two target points. ### Claim 13 (depends on 12) The computing device according to claim 12, wherein the weight coefficient comprises a weight coefficient of a first component, a weight coefficient of a second component, and a weight coefficient of a third component; the weight coefficient of the first component, the weight coefficient of the second component, and the weight coefficient of the third component corresponding to the same group in the at least one group are all equal; or, at least two coefficients from among the weight coefficient of the first component, the weight coefficient of the second component, and the weight coefficient of the third component corresponding to the same group in the at least one group are unequal. ### Claim 14 (depends on 12) The computing device according to claim 12, wherein the weight coefficient comprises a weight coefficient of a first component, a weight coefficient of a second component, and a weight coefficient of a third component; and the determining the weight coefficient of each of the at least two target points according to the geometry information of each of the at least two target points comprises: determining a first distribution value of the at least two target points in a first component direction, a second distribution value of the at least two target points in a second component direction, and a third distribution value of the at least two target points in a third component direction respectively according to the geometry information of each of the at least two target points; and determining the weight coefficient of each of the at least two target points according to the first distribution value, the second distribution value, and the third distribution value. ### Claim 15 (depends on 14) The computing device according to claim 14, wherein the determining a first distribution value of the at least two target points in a first component direction, a second distribution value of the at least two target points in a second component direction, and a third distribution value of the at least two target points in a third component direction respectively according to the geometry information of each of the at least two target points comprises: determining a first value range of the at least two target points in the first component direction according to the geometry information of each of the at least two target points in the first component direction; determining a second value range of the at least two target points in the second component direction according to the geometry information of each of the at least two target points in the second component direction; determining a third value range of the at least two target points in the third component direction according to the geometry information of each of the at least two target points in the third component direction; and determining the first distribution value, the second distribution value, and the third distribution value according to the first value range, the second value range, and the third value range. ### Claim 16 (depends on 15) The computing device according to claim 15, wherein the determining the first distribution value, the second distribution value, and the third distribution value according to the first value range, the second value range, and the third value range comprises: determining a range value of the first value range as the first distribution value; determining a range value of the second value range as the second distribution value; and determining a range value of the third value range as the third distribution value. ### Claim 17 (depends on 15) The computing device according to claim 15, wherein the determining the first distribution value, the second distribution value, and the third distribution value according to the first value range, the second value range, and the third value range comprises: determining a first ratio of the number of the at least two target points to the range value of the first value range, and determining the first ratio as the first distribution value; determining a second ratio of the number of the at least two target points to the range value of the second value range, and determining the second ratio as the second distribution value; and determining a third ratio of the number of the at least two target points to the range value of the third value range, and determining the third ratio as the third distribution value. ### Claim 18 (depends on 14) The computing device according to claim 14, wherein the determining a first distribution value of the at least two target points in a first component direction, a second distribution value of the at least two target points in a second component direction, and a third distribution value of the at least two target points in a third component direction respectively according to the geometry information of each of the at least two target points comprises: determining a first variance of the at least two target points in the first component direction according to the geometry information of each of the at least two target points in the first component direction; determining a second variance of the at least two target points in the second component direction according to the geometry information of each of the at least two target points in the second component direction; determining a third variance of the at least two target points in the third component direction according to the geometry information of each of the at least two target points in the third component direction; and determining the first distribution value, the second distribution value, and the third distribution value according to the first variance, the second variance, and the third variance. ### Claim 19 (depends on 12) The computing device according to claim 12, wherein the weight coefficient comprises a weight coefficient of a first component, a weight coefficient of a second component, and a weight coefficient of a third component; and the determining the weight coefficient of each of the at least two target points according to attribute information of each of the at least two target points comprises: determining, according to the geometry information of each of the at least two target points, a center point of a region enclosed by the at least two target points; determining, respectively from among the at least two target points, a first point that is farthest to the center point in the first component direction, a second point that is farthest to the center point in the second component direction, and a third point that is farthest to the center point in the third component direction; determining the first distribution value of the at least two target points in the first component direction, the second distribution value of the at least two target points in the second component direction, and the third distribution value of the at least two target points in the third component direction respectively according to the attribute information of each of the first point, the second point, and the third point; and determining the weight coefficient of each of the at least two target points according to the first distribution value, the second distribution value, and the third distribution value. ### Claim 20 A non-transitory computer-readable storage medium storing computer-readable instructions that, when executed by a processor of a computer device, causes the computer device to implement a method for selecting a neighbor point of a current point in a point cloud including: determining, from point cloud data, a target region where the current point is located, the target region comprising a plurality of points; determining, for at least two decoded target points in the target region, a weight coefficient of each of the at least two target points, the at least two target points not comprising the current point, wherein the weight coefficient is a preset fixed value; determining a weight of each of the at least two target points according to the weight coefficient and a distance between each of the at least two target points and the current point according to geometry information of each of the at least two target points and geometry information of the current point; and selecting at least one from the at least two target points according to the weight of each of the at least two target points as the neighbor point of the current point.