# US 12,113,980 B2 · Video colour component prediction method and apparatus, and computer storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,113,980 B2 - Document ID: US12113980B2 - Status: Granted - Kind: B2 - Application number: 18/353,210 - Filed: 2023-07-17 - Published: 2023-11-09 - Granted: 2024-10-08 - Earliest claimed: 2018-08-09 - Assignees: Guangdong Oppo Mobile Telecommunications Corp., Ltd. - Applicants: Guangdong Oppo Mobile Telecommunications Corp., Ltd. - Inventors: Junyan Huo; Xiaoyan Chai; Yanzhuo Ma; Fuzheng Yang - Web page: https://patentgrep.com/patent/US12113980B2 ## CPC - 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 19/126: Details of normalisation or weighting functions, e.g. normalisation matrices or variable uniform quantisers - G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model - H04N 19/136: Incoming video signal characteristics or properties - H04N 19/176: the region being a block, e.g. a macroblock - H04N 19/182: the unit being a pixel - H04N 19/186: the unit being a colour or a chrominance component - H04N 19/593: involving spatial prediction techniques - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A video colour component prediction method and apparatus, and a computer storage medium are provided. The prediction method includes: obtaining a first colour component neighboring reference value and a first colour component reconstructed value corresponding to a current coding block, wherein the first colour component neighboring reference value represents a first colour component parameter corresponding to a neighboring reference sample of the current coding block, and the first colour component reconstructed value represents one or more reconstruction parameters of a first colour component corresponding to the current coding block; determining a weight coefficient corresponding to the neighboring reference sample; determining a scale factor according to the weight coefficient and the first colour component neighboring reference value; and obtaining a second colour component predicted value corresponding to the current coded block based on a linear model corresponding to the scale factor. ## Claims ### Claim 1 A method for decoding a video, comprising: acquiring a first colour component neighboring reference value, a second colour component neighboring reference value and a first colour component reconstructed value corresponding to a current block, wherein the first colour component neighboring reference value is indicative of a first colour component parameter corresponding to a neighboring reference sample of the current block, the second colour component neighboring reference value is indicative of a second colour component parameter corresponding to the neighboring reference sample of the current block, and the first colour component reconstructed value is indicative of one or more reconstructed parameters of a first colour component corresponding to the current block; generating a second colour component predicted value corresponding to the current block at least based on a linear model corresponding to factors, wherein the factors are determined by at least one of a weight coefficient, the first colour component neighboring reference value, or the second colour component neighboring reference value; and decoding the video based on the second colour component predicted value. ### Claim 2 (depends on 1) The method of claim 1, further comprising: generating the second colour component predicted value based on the linear model corresponding to the factors and the first colour component reconstructed value. ### Claim 3 (depends on 1) The method of claim 1, wherein a position of the current block is indicative of a position correlation between the current block and the neighboring reference sample. ### Claim 4 (depends on 1) The method of claim 1, further comprising: acquiring a second colour component estimated value corresponding to the current block by performing component prediction according to a second colour component corresponding to the current block. ### Claim 5 (depends on 1) The method of claim 1, further comprising: performing downsampling on the neighboring reference sample to determine part of reference samples based on a preset threshold. ### Claim 6 (depends on 1) The method of claim 1, wherein the neighboring reference sample comprises at least one of: an upper reference sample of the current block, an upper-left reference sample of the current block; or a left reference sample of the current block. ### Claim 7 A decoding apparatus, comprising: a processor; and a memory storing an instruction executable by the processor, wherein when the instruction is executed, the processor is configured to: acquire a first colour component neighboring reference value, a second colour component neighboring reference value and a first colour component reconstructed value corresponding to a current block, wherein the first colour component neighboring reference value is indicative of a first colour component parameter corresponding to a neighboring reference sample of the current block, the second colour component neighboring reference value is indicative of a second colour component parameter corresponding to the neighboring reference sample of the current block, and the first colour component reconstructed value is indicative of one or more reconstructed parameters of a first colour component corresponding to the current block; generate a second colour component predicted value corresponding to the current block at least based on a linear model corresponding to factors, wherein the factors are determined by at least one of a weight coefficient, the first colour component neighboring reference value, or the second colour component neighboring reference value; and decode the current block based on the second colour component predicted value. ### Claim 8 (depends on 7) The apparatus of claim 7, wherein the processor is further configured to: generate the second colour component predicted value based on the linear model corresponding to the factors and the first colour component reconstructed value. ### Claim 9 (depends on 7) The apparatus of claim 7, wherein a position of the current block is indicative of a position correlation between the current block and the neighboring reference sample. ### Claim 10 (depends on 7) The apparatus of claim 7, wherein the processor is further configured to: acquire a second colour component estimated value corresponding to the current block by performing component prediction according to a second colour component corresponding to the current block. ### Claim 11 (depends on 7) The apparatus of claim 7, wherein the processor is further configured to: perform downsampling on the neighboring reference sample to determine part of reference samples based on a preset threshold. ### Claim 12 (depends on 7) The apparatus of claim 7, wherein the neighboring reference sample comprises at least one of: an upper reference sample of the current block, an upper-left reference sample of the current block; or a left reference sample of the current block. ### Claim 13 A method for encoding a video, comprising: determining a first colour component neighboring reference value, a second colour component neighboring reference value and a first colour component reconstructed value corresponding to a current block, wherein the first colour component neighboring reference value is indicative of a first colour component parameter corresponding to a neighboring reference sample of the current block, the second colour component neighboring reference value is indicative of a second colour component parameter corresponding to the neighboring reference sample of the current block, and the first colour component reconstructed value is indicative of one or more reconstructed parameters of a first colour component corresponding to the current block; determining a second colour component predicted value corresponding to the current block at least based on a linear model corresponding to factors, wherein the factors are determined by at least one of a weight coefficient, the first colour component neighboring reference value, or the second colour component neighboring reference value; and encoding the video based on the second colour component predicted value. ### Claim 14 (depends on 13) The method of claim 13, further comprising: determining the second colour component predicted value based on the linear model corresponding to the factors and the first colour component reconstructed value. ### Claim 15 (depends on 13) The method of claim 13, wherein a position of the current block is indicative of a position correlation between the current block and the neighboring reference sample. ### Claim 16 (depends on 13) The method of claim 13, further comprising: determining a second colour component estimated value corresponding to the current block by performing component prediction according to a second colour component corresponding to the current block. ### Claim 17 (depends on 13) The method of claim 13, further comprising: performing downsampling on the neighboring reference sample to determine part of reference samples based on a preset threshold. ### Claim 18 (depends on 13) The method of claim 13, wherein the neighboring reference sample comprises at least one of: an upper reference sample of the current block, an upper-left reference sample of the current block; or a left reference sample of the current block.