# US 11,443,477 B2 · Methods and systems for generating a volumetric two-dimensional representation of a three-dimensional object > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,477 B2 - Document ID: US11443477B2 - Status: Granted - Kind: B2 - Application number: 17/112,333 - Filed: 2020-12-04 - Published: 2022-06-09 - Granted: 2022-09-13 - Earliest claimed: 2020-12-04 - Assignees: Verizon Patent and Licensing Inc. - Applicants: Verizon Patent and Licensing Inc. - Inventors: Garry Guan - Web page: https://patentgrep.com/patent/US11443477B2 ## CPC - G06T 15/00: Three-dimensional [3D] image rendering - G06T 15/08: Volume rendering - G06T 7/0002: {Inspection of images, e.g. flaw detection} - G06T 17/00: Three-dimensional [3D] modelling for computer graphics - G06T 19/00: Manipulating three-dimensional [3D] models or images for computer graphics - G06T 2207/20081: Training; Learning - G06T 2207/30168: Image quality inspection - G06T 2210/12: Bounding box - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract An illustrative image processing system identifies a component of a three-dimensional (3D) object that is to be presented to a user. The image processing system then generates a set of two-dimensional (2D) images depicting the component of the 3D object from a set of vantage points tailored to the component. The image processing system incorporates one or more 2D images of this set of 2D images within a 2D atlas image associated with the 3D object. The image processing system provides the 2D atlas image to a volumetric rendering device configured to render, based on the 2D atlas image, a volumetric representation of the 3D object for presentation to the user. Corresponding methods and systems are also disclosed. ## Claims ### Claim 1 A method comprising: identifying, by an image processing system, a first component of a three-dimensional (3D) object that is to be presented to a user, the first component of the 3D object distinguishable from one or more other components of the 3D object; generating, by the image processing system, a first set of two-dimensional (2D) images depicting the first component of the 3D object from a first set of vantage points tailored to the first component by corresponding to faces of a virtual bounding box encapsulating the first component; identifying, by the image processing system from among the first set of 2D images, a particular 2D image depicting the first component from a particular vantage point located internally within the 3D object; incorporating, by the image processing system within a 2D atlas image associated with the 3D object, each of the first set of 2D images except the particular 2D image identified as depicting the first component from the particular vantage point located internally within the 3D object; and providing, by the image processing system, the 2D atlas image to a volumetric rendering device configured to render, based on the 2D atlas image, a volumetric representation of the 3D object for presentation to the user. ### Claim 2 (depends on 1) The method of claim 1, further comprising: identifying, by the image processing system, a second component of the 3D object included among the one or more other components of the 3D object; generating, by the image processing system, a second set of 2D images depicting the second component of the 3D object from a second set of vantage points tailored to the second component and different from the first set of vantage points; and incorporating, by the image processing system within the 2D atlas image associated with the 3D object, one or more 2D images of the second set of 2D images. ### Claim 3 (depends on 1) The method of claim 1, wherein the first set of 2D images includes: color data images depicting the first component from each of the first set of vantage points; and depth data images depicting the first component from each of the first set of vantage points. ### Claim 4 (depends on 1) The method of claim 1, further comprising: accessing, by the image processing system, a representation of a scene that includes a plurality of 3D objects including the 3D object; and identifying, by the image processing system within the representation of the scene, the 3D object as being of a recognized object type; wherein the identifying of the first component of the 3D object is based on the identifying of the 3D object as being of the recognized object type. ### Claim 5 (depends on 4) The method of claim 4, further comprising obtaining, by the image processing system in response to the identifying of the 3D object as being of the recognized object type, a machine learning model associated with the recognized object type; wherein the identifying of the first component of the 3D object based on the identifying of the 3D object as being of the recognized object type is performed by identifying the first component of the 3D object based on the machine learning model obtained in response to the identifying of the 3D object as being of the recognized object type. ### Claim 6 (depends on 1) The method of claim 1, wherein the generating of the first set of 2D images includes filtering out, based on the identifying of the first component, content other than the first component from each 2D image of the first set of 2D images. ### Claim 7 (depends on 1) The method of claim 1, wherein the virtual bounding box dynamically changes to continuously encapsulate the first component such that the vantage points of the first set of vantage points are dynamic vantage points configured to remain tailored to the first component as the first component changes with respect to attributes including: a size attribute, an aspect ratio attribute, a position attribute, and an orientation attribute. ### Claim 8 (depends on 1) The method of claim 1, wherein: the first set of vantage points are orthographic vantage points; and the first set of 2D images are generated to orthographically depict the first component of the 3D object. ### Claim 9 (depends on 1) The method of claim 1, wherein the volumetric rendering device is a media player device used by the user and configured to present the volumetric representation of the 3D object to the user. ### Claim 10 A system comprising: a memory storing instructions; and a processor communicatively coupled to the memory and configured to execute the instructions to: identify a first component of a three-dimensional (3D) object that is to be presented to a user, the first component of the 3D object distinguishable from one or more other components of the 3D object; generate a first set of two-dimensional (2D) images depicting the first component of the 3D object from a first set of vantage points tailored to the first component by corresponding to faces of a virtual bounding box encapsulating the first component; identify, from among the first set of 2D images, a particular 2D image depicting the first component from a particular vantage point located internally within the 3D object; incorporate, within a 2D atlas image associated with the 3D object, each of the first set of 2D images except the particular 2D image identified as depicting the first component from the particular vantage point located internally within the 3D object; and provide the 2D atlas image to a volumetric rendering device configured to render, based on the 2D atlas image, a volumetric representation of the 3D object for presentation to the user. ### Claim 11 (depends on 10) The system of claim 10, wherein the processor is further configured to execute the instructions to: identify a second component of the 3D object included among the one or more other components of the 3D object; generate a second set of 2D images depicting the second component of the 3D object from a second set of vantage points tailored to the second component and different from the first set of vantage points; and incorporate, within the 2D atlas image associated with the 3D object, one or more 2D images of the second set of 2D images. ### Claim 12 (depends on 10) The system of claim 10, wherein the first set of 2D images includes: color data images depicting the first component from each of the first set of vantage points; and depth data images depicting the first component from each of the first set of vantage points. ### Claim 13 (depends on 10) The system of claim 10, wherein: the processor is further configured to execute the instructions to: access a representation of a scene that includes a plurality of 3D objects including the 3D object, and identify, within the representation of the scene, the 3D object as being of a recognized object type; and the identifying of the first component of the 3D object is based on the identifying of the 3D object as being of the recognized object type. ### Claim 14 (depends on 13) The system of claim 13, wherein: the processor is further configured to execute the instructions to obtain, in response to the identifying of the 3D object as being of the recognized object type, a machine learning model associated with the recognized object type; and the identifying of the first component of the 3D object based on the identifying of the 3D object as being of the recognized object type is performed by identifying the first component of the 3D object based on the machine learning model obtained in response to the identifying of the 3D object as being of the recognized object type. ### Claim 15 (depends on 10) The system of claim 10, wherein the generating of the first set of 2D images includes filtering out, based on the identifying of the first component, content other than the first component from each 2D image of the first set of 2D images. ### Claim 16 (depends on 10) The system of claim 10, wherein the virtual bounding box dynamically changes to continuously encapsulate the first component such that the vantage points of the first set of vantage points are dynamic vantage points configured to remain tailored to the first component as the first component changes with respect to attributes including: a size attribute, an aspect ratio attribute, a position attribute, and an orientation attribute. ### Claim 17 (depends on 10) The system of claim 10, wherein: the first set of vantage points are orthographic vantage points; and the first set of 2D images are generated to orthographically depict the first component of the 3D object. ### Claim 18 (depends on 10) The system of claim 10, wherein the volumetric rendering device is a media player device used by the user and configured to present the volumetric representation of the 3D object to the user. ### Claim 19 A non-transitory computer-readable medium storing instructions that, when executed, direct a processor of a computing device to: identify a first component of a three-dimensional (3D) object that is to be presented to a user, the first component of the 3D object distinguishable from one or more other components of the 3D object; generate a first set of two-dimensional (2D) images depicting the first component of the 3D object from a first set of vantage points tailored to the first component by corresponding to faces of a virtual bounding box encapsulating the first component; identify, from among the first set of 2D images, a particular 2D image depicting the first component from a particular vantage point located internally within the 3D object; incorporate, within a 2D atlas image associated with the 3D object, each of the first set of 2D images except the particular 2D image identified as depicting the first component from the particular vantage point located internally within the 3D object; and provide the 2D atlas image to a volumetric rendering device configured to render, based on the 2D atlas image, a volumetric representation of the 3D object for presentation to the user. ### Claim 20 (depends on 19) The computer-readable medium of claim 19, wherein the virtual bounding box dynamically changes to continuously encapsulate the first component such that the vantage points of the first set of vantage points are dynamic vantage points configured to remain tailored to the first component as the first component changes with respect to attributes including: a size attribute, an aspect ratio attribute, a position attribute, and an orientation attribute.