# US 11,910,017 B2 · Method for predicting point cloud attribute, encoder, decoder, and storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,910,017 B2 - Document ID: US11910017B2 - Status: Granted - Kind: B2 - Application number: 17/972,005 - Filed: 2022-10-24 - Published: 2023-02-16 - Granted: 2024-02-20 - Earliest claimed: 2020-12-07 - Assignees: Tencent Technology (Shenzhen) Company Limited - Applicants: Tencent Technology (Shenzhen) Company Limited - Inventors: Wenjie Zhu - Web page: https://patentgrep.com/patent/US11910017B2 ## CPC - G06T 9/001: {Model-based coding, e.g. wire frame} - H04N 19/597: specially adapted for multi-view video sequence encoding - G06T 9/004: {Predictors, e.g. intraframe, interframe coding} - H04N 19/136: Incoming video signal characteristics or properties - H04N 19/42: characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation (H04N19/635 takes precedence) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract This application provides a method for predicting a point cloud attribute, an encoder, a decoder, and a storage medium. During point cloud attribute prediction, different selection policies for target adjacent points are designed according to the distribution of repetition points, to determine at least one target adjacent point of a target point, and attribute prediction is performed on the target point according to reconstructed attribute information of the at least one target adjacent point, thereby improving the efficiency and accuracy of point cloud attribute prediction. ## Claims ### Claim 1 A method for predicting a point cloud attribute, the method comprising: acquiring, by a device comprising a memory storing instructions and a processor in communication with the memory, N encoded points closest to a target point from point cloud data as N adjacent points of the target point, the target point being one of points in the point cloud data; acquiring, by the device, K first-group adjacent points from the N adjacent points, the K first-group adjacent points comprising M repetition points with same position information; determining, by the device, at least one target adjacent point of the target point according to the M repetition points; and performing, by the device, attribute prediction on the target point according to reconstructed attribute information of the at least one target adjacent point, wherein each of N, K, and M is a positive integer. ### Claim 2 (depends on 1) The method according to claim 1, further comprising: using K−M first-group adjacent points other than the M repetition points in the K first-group adjacent points as K−M target adjacent points of the target point. ### Claim 3 (depends on 1) The method according to claim 1, wherein the determining the at least one target adjacent point of the target point according to the M repetition points comprises: determining one third-group adjacent point from the M repetition points; and using the third-group adjacent point as one target adjacent point of the target point. ### Claim 4 (depends on 3) The method according to claim 3, further comprising: using an attribute value of any one of the M repetition points as an attribute value of the third-group adjacent point; or using an average value of attribute values of all the M repetition points as an attribute value of the third-group adjacent point. ### Claim 5 (depends on 3) The method according to claim 3, further comprising: selecting M−1 second-group adjacent points from the N adjacent points, the M−1 second-group adjacent points being different from the K first-group adjacent points; and using the M−1 second-group adjacent points as M−1 target adjacent points of the target point. ### Claim 6 (depends on 5) The method according to claim 5, wherein the selecting M−1 second-group adjacent points from the N adjacent points comprises: selecting M−1 adjacent points closest to the target point from N−K adjacent points as the M−1 second-group adjacent points, the N−K adjacent points being adjacent points other than the K first-group adjacent points in the N adjacent points. ### Claim 7 (depends on 1) The method according to claim 1, wherein the acquiring K first-group adjacent points from the N adjacent points comprises: determining a distance between each of the N adjacent points and the target point according to position information of each of the N adjacent points and position information of the target point; and using first K adjacent points with the shortest distance in the N adjacent points as the K first-group adjacent points. ### Claim 8 An apparatus for predicting a point cloud attribute, the apparatus comprising: a memory storing instructions; and a processor in communication with the memory, wherein, when the processor executes the instructions, the processor is configured to cause the apparatus to perform: acquiring N encoded points closest to a target point from point cloud data as N adjacent points of the target point, the target point being one of points in the point cloud data; acquiring K first-group adjacent points from the N adjacent points, the K first-group adjacent points comprising M repetition points with same position information; determining at least one target adjacent point of the target point according to the M repetition points; and performing attribute prediction on the target point according to reconstructed attribute information of the at least one target adjacent point, wherein each of N, K, and M is a positive integer. ### Claim 9 (depends on 8) The apparatus according to claim 8, wherein, when the processor executes the instructions, the processor is configured to further cause the apparatus to perform: using K−M first-group adjacent points other than the M repetition points in the K first-group adjacent points as K−M target adjacent points of the target point. ### Claim 10 (depends on 8) The apparatus according to claim 8, wherein, when the processor is configured to cause the apparatus to perform determining the at least one target adjacent point of the target point according to the M repetition points, the processor is configured to cause the apparatus to perform: determining one third-group adjacent point from the M repetition points; and using the third-group adjacent point as one target adjacent point of the target point. ### Claim 11 (depends on 10) The apparatus according to claim 10, wherein, when the processor executes the instructions, the processor is configured to further cause the apparatus to perform: using an attribute value of any one of the M repetition points as an attribute value of the third-group adjacent point; or using an average value of attribute values of all the M repetition points as an attribute value of the third-group adjacent point. ### Claim 12 (depends on 10) The apparatus according to claim 10, wherein, when the processor executes the instructions, the processor is configured to further cause the apparatus to perform: selecting M−1 second-group adjacent points from the N adjacent points, the M−1 second-group adjacent points being different from the K first-group adjacent points; and using the M−1 second-group adjacent points as M−1 target adjacent points of the target point. ### Claim 13 (depends on 12) The apparatus according to claim 12, wherein, when the processor is configured to cause the apparatus to perform selecting M−1 second-group adjacent points from the N adjacent points, the processor is configured to cause the apparatus to perform: selecting M−1 adjacent points closest to the target point from N−K adjacent points as the M−1 second-group adjacent points, the N−K adjacent points being adjacent points other than the K first-group adjacent points in the N adjacent points. ### Claim 14 (depends on 8) The apparatus according to claim 8, wherein, when the processor is configured to cause the apparatus to perform acquiring K first-group adjacent points from the N adjacent points, the processor is configured to cause the apparatus to perform: determining a distance between each of the N adjacent points and the target point according to position information of each of the N adjacent points and position information of the target point; and using first K adjacent points with the shortest distance in the N adjacent points as the K first-group adjacent points. ### Claim 15 A non-transitory computer-readable storage medium, configured to store computer-readable instructions, wherein, the computer-readable instructions, when executed by a processor, are configured to cause the processor to perform: acquiring N encoded points closest to a target point from point cloud data as N adjacent points of the target point, the target point being one of points in the point cloud data; acquiring K first-group adjacent points from the N adjacent points, the K first-group adjacent points comprising M repetition points with same position information; determining at least one target adjacent point of the target point according to the M repetition points; and performing attribute prediction on the target point according to reconstructed attribute information of the at least one target adjacent point, wherein each of N, K, and M is a positive integer. ### Claim 16 (depends on 15) The non-transitory computer-readable storage medium according to claim 15, wherein, when the computer-readable instructions are executed by the processor, the computer-readable instructions are configured to further cause the processor to perform: using K−M first-group adjacent points other than the M repetition points in the K first-group adjacent points as K−M target adjacent points of the target point. ### Claim 17 (depends on 15) The non-transitory computer-readable storage medium according to claim 15, wherein, when the computer-readable instructions are configured to cause the processor to perform determining the at least one target adjacent point of the target point according to the M repetition points, the computer-readable instructions are configured to cause the processor to perform: determining one third-group adjacent point from the M repetition points; and using the third-group adjacent point as one target adjacent point of the target point. ### Claim 18 (depends on 17) The non-transitory computer-readable storage medium according to claim 17, wherein, when the computer-readable instructions are executed by the processor, the computer-readable instructions are configured to further cause the processor to perform: using an attribute value of any one of the M repetition points as an attribute value of the third-group adjacent point; or using an average value of attribute values of all the M repetition points as an attribute value of the third-group adjacent point. ### Claim 19 (depends on 17) The non-transitory computer-readable storage medium according to claim 17, wherein, when the computer-readable instructions are executed by the processor, the computer-readable instructions are configured to further cause the processor to perform: selecting M−1 second-group adjacent points from the N adjacent points, the M−1 second-group adjacent points being different from the K first-group adjacent points; and using the M−1 second-group adjacent points as M−1 target adjacent points of the target point. ### Claim 20 (depends on 19) The non-transitory computer-readable storage medium according to claim 19, wherein, when the computer-readable instructions are configured to cause the processor to perform selecting M−1 second-group adjacent points from the N adjacent points, the computer-readable instructions are configured to cause the processor to perform: selecting M−1 adjacent points closest to the target point from N−K adjacent points as the M−1 second-group adjacent points, the N−K adjacent points being adjacent points other than the K first-group adjacent points in the N adjacent points.