# US 2025/0157084 A1 · Reflection prediction and across-parallelogram prediction in polygonal mesh compression > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0157084 A1 - Document ID: US20250157084A1 - Status: Published application - Kind: A1 - Application number: 18/923,663 - Filed: 2024-10-22 - Published: 2025-05-15 - Earliest claimed: 2023-11-09 - Assignees: Tencent America LLC - Applicants: Tencent America LLC - Inventors: Chao HUANG; Thuong NGUYEN CANH; Xiaozhong XU; Shan LIU - Web page: https://patentgrep.com/patent/US20250157084A1 ## CPC - G06T 9/001: {Model-based coding, e.g. wire frame} - G06T 9/004: {Predictors, e.g. intraframe, interframe coding} - G06T 15/506: {Illumination models} - H04N 19/70: characterised by syntax aspects related to video coding, e.g. related to compression standards - H04N 19/91: Entropy coding, e.g. variable length coding [VLC] or arithmetic coding - G06T 2210/32: Image data format - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract Aspects of the disclosure includes methods and apparatuses for coding a mesh. A method for decoding a mesh includes: receiving coded information including a syntax element indicating one of an across-parallelogram prediction and a reflection prediction to predict a position of one of a current vertex of the mesh and a current point of a two-dimensional (2D) map that is associated with the mesh, determining the one of the across-parallelogram prediction and the reflection prediction to predict the position of the one of the current vertex of the mesh and the current point of the 2D map based on the syntax element, and predicting the position of the one of the current vertex of the mesh and the current point of the 2D map using the determined one of the across-parallelogram prediction and the reflection prediction. ## Claims ### Claim 1 A method for decoding a mesh, the method comprising: receiving coded information including a syntax element indicating one of an across-parallelogram prediction and a reflection prediction to predict a position of one of a current vertex of the mesh and a current point of a two-dimensional (2D) map that is associated with the mesh; determining the one of the across-parallelogram prediction and the reflection prediction to predict the position of the one of the current vertex of the mesh and the current point of the 2D map based on the syntax element; and predicting the position of the one of the current vertex of the mesh and the current point of the 2D map using the determined one of the across-parallelogram prediction and the reflection prediction. ### Claim 2 (depends on 1) The method of claim 1, wherein the determining comprises: determining a context based on whether a previously signaled prediction is the across-parallelogram prediction or the reflection prediction; and decoding the syntax element using context modeling with the determined context. ### Claim 3 (depends on 2) The method of claim 2, wherein the context is a first context when the previously signaled prediction is the across-parallelogram prediction; the context is a second context when the previously signaled prediction is the reflection prediction; and the first context and the second context are different. ### Claim 4 (depends on 1) The method of claim 1, wherein the mesh is a three-dimensional (3D) mesh, the one of the current vertex of the mesh and the current point of the 2D map is the current vertex of the 3D mesh, and the position of the current vertex is indicated by a 3D coordinate. ### Claim 5 (depends on 4) The method of claim 4, wherein the current vertex of the mesh is incident to a current face of the mesh, and when the across-parallelogram prediction is determined as the one of the across-parallelogram prediction and the reflection prediction, the predicting includes predicting the position of the current vertex using a parallelogram that is based on three vertices incident to a neighboring face of the current face, two of the three vertices being incident to the neighboring face and the current face. ### Claim 6 (depends on 4) The method of claim 4, wherein the current vertex of the mesh is incident to a current face of the mesh, and when the reflection prediction is determined as the one of the across-parallelogram prediction and the reflection prediction, the predicting includes predicting the position of the current vertex using a reflection of a first vertex with respect to a line passing through a second vertex and a third vertex, the first vertex being incident onto a neighboring face of the current face, the second vertex and the third vertex being incident to the neighboring face. ### Claim 7 (depends on 1) The method of claim 1, wherein the mesh is a three-dimensional (3D) mesh, the 2D map is a UV map associated with the 3D mesh, the one of the current vertex of the mesh and the current point of the 2D map is the current point of the UV map, the current point of the UV map is indicated by a UV coordinate. ### Claim 8 A method for encoding a mesh, the method comprising: determining one of an across-parallelogram prediction and a reflection prediction to predict a position of one of a current vertex of the mesh and a current point of a two-dimensional (2D) map that is associated with the mesh; predicting the position of the one of the current vertex of the mesh and the current point of the 2D map using the one of the across-parallelogram prediction and the reflection prediction; determining a context to encode the one of the across-parallelogram prediction and the reflection prediction based on whether a previously encoded position is encoded using the across-parallelogram prediction or the reflection prediction; and encoding a syntax element indicating the one of the across-parallelogram prediction and the reflection prediction using context modeling with the determined context. ### Claim 9 (depends on 8) The method of claim 8, wherein the context is a first context when the previously encoded position is encoded using the across-parallelogram prediction; the context is a second context when the previously encoded position is encoded using the reflection prediction; and the first context and the second context are different. ### Claim 10 (depends on 8) The method of claim 8, wherein the mesh is a three-dimensional (3D) mesh, the one of the current vertex of the mesh and the current point of the 2D map is the current vertex of the 3D mesh, and the position of the current vertex is indicated by a 3D coordinate. ### Claim 11 (depends on 10) The method of claim 10, wherein the current vertex of the mesh is incident to a current face of the mesh, and when the across-parallelogram prediction is determined as the one of the across-parallelogram prediction and the reflection prediction, the predicting the position includes predicting the position of the current vertex using a parallelogram that is based on three vertices incident to a neighboring face of the current face, two of the three vertices being incident to the neighboring face and the current face. ### Claim 12 (depends on 10) The method of claim 10, wherein the current vertex of the mesh is incident to a current face of the mesh, and when the reflection prediction is determined as the one of the across-parallelogram prediction and the reflection prediction, the predicting includes predicting the position of the current vertex using a reflection of a first vertex with respect to a line passing through a second vertex and a third vertex, the first vertex being incident onto a neighboring face of the current face, the second vertex and the third vertex being incident to the neighboring face. ### Claim 13 (depends on 8) The method of claim 8, wherein the mesh is a three-dimensional (3D) mesh, the 2D map is a UV map associated with the 3D mesh, the one of the current vertex of the mesh and the current point of the 2D map is the current point of the UV map, the current point of the UV map is indicated by a UV coordinate. ### Claim 14 (depends on 8) The method of claim 8, wherein the determining the one of the across-parallelogram prediction and the reflection prediction comprises: performing the across-parallelogram prediction to obtain a first residual indicating a first corrective vector between a first predicted position and the position of the one of the current vertex of the mesh and the current point of the 2D map; performing the reflection prediction to obtain a second residual indicating a second corrective vector between a second predicted position and the position of the one of the current vertex of the mesh and the current point of the 2D map; and determining the one of the across-parallelogram prediction and the reflection prediction corresponding to the minimum of the first residual and the second residual. ### Claim 15 A method of processing a mesh, the method comprising: processing a bitstream of the mesh according to a format rule, the bitstream includes a syntax element indicating one of an across-parallelogram prediction and a reflection prediction to predict a position of one of a current vertex of the mesh and a current point of a two-dimensional (2D) map that is associated with the mesh, and the format rule specifies that the one of the across-parallelogram prediction and the reflection prediction to predict the position of the one of the current vertex of the mesh and the current point of the 2D map is determined based on the syntax element; and the position of the one of the current vertex of the mesh and the current point of the 2D map is predicted using the determined one of the across-parallelogram prediction and the reflection prediction. ### Claim 16 (depends on 15) The method of claim 15, wherein the format rule specifies that: a context is determined based on whether a previously signaled prediction is the across-parallelogram prediction or the reflection prediction; and the syntax element is decoded using context modeling with the determined context. ### Claim 17 (depends on 16) The method of claim 16, wherein the context is a first context when the previously signaled prediction is the across-parallelogram prediction; the context is a second context when the previously signaled prediction is the reflection prediction; and the first context and the second context are different. ### Claim 18 (depends on 15) The method of claim 15, wherein the mesh is a three-dimensional (3D) mesh, the one of the current vertex of the mesh and the current point of the 2D map is the current vertex of the 3D mesh, and the position of the current vertex is indicated by a 3D coordinate. ### Claim 19 (depends on 18) The method of claim 18, wherein the current vertex of the mesh is incident to a current face of the mesh, and the format rule specifies that when the across-parallelogram prediction is determined as the one of the across-parallelogram prediction and the reflection prediction, the position of the current vertex is predicted using a parallelogram that is based on three vertices incident to a neighboring face of the current face, two of the three vertices being incident to the neighboring face and the current face. ### Claim 20 (depends on 18) The method of claim 18, wherein the current vertex of the mesh is incident to a current face of the mesh, and the format rule specifies that when the reflection prediction is determined as the one of the across-parallelogram prediction and the reflection prediction, the position of the current vertex is predicted using a reflection of a first vertex with respect to a line passing through a second vertex and a third vertex, the first vertex being incident onto a neighboring face of the current face, the second vertex and the third vertex being incident to the neighboring face.