# US 2020/0401788 A1 · Distinguishing an image of a three-dimensional object from an image of a two-dimensional rendering of an object > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0401788 A1 - Document ID: US20200401788A1 - Status: Published application - Kind: A1 - Application number: 16/444,574 - Filed: 2019-06-18 - Published: 2020-12-24 - Earliest claimed: 2019-06-18 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: David Okun; Justin Mccoy - Web page: https://patentgrep.com/patent/US20200401788A1 ## CPC - H04N 13/271: wherein the generated image signals comprise depth maps or disparity maps - G06F 18/2413: based on distances to training or reference patterns - G06V 20/64: Three-dimensional [3D] objects - G06V 20/647: {by matching two-dimensional images to three-dimensional objects} - H04N 13/239: using two two-dimensional [2D] image sensors having a relative position equal to or related to the interocular distance (H04N13/243 takes precedence) - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract An image classification model is configured to classify a subject viewed via a multi-camera apparatus. A depth classification model is configured to distinguish between a depth characteristic of a 3D subject and a depth characteristic of a realistic 2D rendering of a 3D subject, using depth information provided by viewing a subject via a multi-camera apparatus. A 2D rendering of a 3D subject is presented as an input to a multi-camera apparatus, the multi-camera apparatus operating the image classification model and the depth classification model. Using the multi-camera apparatus, a first depth information corresponding to the input is collected. The first depth information is provided to the depth classification model. Responsive to the depth classification model classifying the input as a 2D rendering, the 2D rendering is rejected as being the 3D subject. ## Claims ### Claim 1 A computer-implemented method comprising: presenting a 2D rendering of a 3D subject as an input to a multi-camera apparatus, the multi-camera apparatus operating an image classification model configured to classify a subject viewed via the multi-camera apparatus, and the multi-camera apparatus operating a depth classification model configured to distinguish between a depth characteristic of a 3D subject and a depth characteristic of a realistic 2D rendering of a 3D subject, using depth information provided by viewing a subject via the multi-camera apparatus; collecting, using the multi-camera apparatus, a first depth information corresponding to the input; providing the first depth information to the depth classification model; and rejecting, responsive to the depth classification model classifying the input as a 2D rendering, the 2D rendering as being the 3D subject. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, further comprising: presenting a 3D subject as an input to the multi-camera apparatus; collecting, using the multi-camera apparatus, a second depth information corresponding to the input; providing the second depth information to the depth classification model; and accepting, responsive to the depth classification model classifying the input as a 3D subject, the 3D subject as being the 3D subject. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, further comprising: generating, from a scene presented as an input to the multi-camera apparatus, a depth map corresponding to the input, a greyscale value of a pixel in the depth map corresponding to a distance from the multi-camera apparatus to a portion of the scene. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein configuring a depth classification model to distinguish between a 3D subject and a realistic 2D rendering of a 3D subject comprises training the depth classification model using a first set of depth information and a second set of depth information, the first set of depth information provided by viewing a set of 3D subjects via a multi-camera apparatus, the second set of depth information provided by viewing a set of realistic 2D renderings of the set of 3D subjects via a multi-camera apparatus. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the depth classification model comprises a convolutional neural network model. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein the image classification model comprises a convolutional neural network model configured to classify a subject using a set of image classification training data, a training data in the set of image classification training data comprising an image and a classification corresponding to the image. ### Claim 7 A computer usable program product comprising one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices, the stored program instructions comprising: program instructions to present a 2D rendering of a 3D subject as an input to a multi-camera apparatus, the multi-camera apparatus operating an image classification model configured to classify a subject viewed via the multi-camera apparatus, and the multi-camera apparatus operating a depth classification model configured to distinguish between a depth characteristic of a 3D subject and a depth characteristic of a realistic 2D rendering of a 3D subject, using depth information provided by viewing a subject via the multi-camera apparatus; program instructions to collect, using the multi-camera apparatus, a first depth information corresponding to the input; program instructions to provide the first depth information to the depth classification model; and program instructions to reject, responsive to the depth classification model classifying the input as a 2D rendering, the 2D rendering as being the 3D subject. ### Claim 8 (depends on 7) The computer usable program product of claim 7, further comprising: program instructions to present a 3D subject as an input to the multi-camera apparatus; collecting, using the multi-camera apparatus, a second depth information corresponding to the input; program instructions to provide the second depth information to the depth classification model; and program instructions to accept, responsive to the depth classification model classifying the input as a 3D subject, the 3D subject as being the 3D subject. ### Claim 9 (depends on 7) The computer usable program product of claim 7, further comprising: program instructions to generate, from a scene presented as an input to the multi-camera apparatus, a depth map corresponding to the input, a greyscale value of a pixel in the depth map corresponding to a distance from the multi-camera apparatus to a portion of the scene. ### Claim 10 (depends on 7) The computer usable program product of claim 7, wherein configuring a depth classification model to distinguish between a 3D subject and a realistic 2D rendering of a 3D subject comprises training the depth classification model using a first set of depth information and a second set of depth information, the first set of depth information provided by viewing a set of 3D subjects via a multi-camera apparatus, the second set of depth information provided by viewing a set of realistic 2D renderings of the set of 3D subjects via a multi-camera apparatus. ### Claim 11 (depends on 7) The computer usable program product of claim 7, wherein the depth classification model comprises a convolutional neural network model. ### Claim 12 (depends on 7) The computer usable program product of claim 7, wherein the image classification model comprises a convolutional neural network model configured to classify a subject using a set of image classification training data, a training data in the set of image classification training data comprising an image and a classification corresponding to the image. ### Claim 13 (depends on 7) The computer usable program product of claim 7, wherein the computer usable code is stored in a computer readable storage device in a data processing system, and wherein the computer usable code is transferred over a network from a remote data processing system. ### Claim 14 (depends on 7) The computer usable program product of claim 7, wherein the computer usable code is stored in a computer readable storage device in a server data processing system, and wherein the computer usable code is downloaded over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system. ### Claim 15 A computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising: program instructions to present a 2D rendering of a 3D subject as an input to a multi-camera apparatus, the multi-camera apparatus operating an image classification model configured to classify a subject viewed via the multi-camera apparatus, and the multi-camera apparatus operating a depth classification model configured to distinguish between a depth characteristic of a 3D subject and a depth characteristic of a realistic 2D rendering of a 3D subject, using depth information provided by viewing a subject via the multi-camera apparatus; program instructions to collect, using the multi-camera apparatus, a first depth information corresponding to the input; program instructions to provide the first depth information to the depth classification model; and program instructions to reject, responsive to the depth classification model classifying the input as a 2D rendering, the 2D rendering as being the 3D subject. ### Claim 16 (depends on 15) The computer system of claim 15, further comprising: program instructions to present a 3D subject as an input to the multi-camera apparatus; collecting, using the multi-camera apparatus, a second depth information corresponding to the input; program instructions to provide the second depth information to the depth classification model; and program instructions to accept, responsive to the depth classification model classifying the input as a 3D subject, the 3D subject as being the 3D subject. ### Claim 17 (depends on 15) The computer system of claim 15, further comprising: program instructions to generate, from a scene presented as an input to the multi-camera apparatus, a depth map corresponding to the input, a greyscale value of a pixel in the depth map corresponding to a distance from the multi-camera apparatus to a portion of the scene. ### Claim 18 (depends on 15) The computer system of claim 15, wherein configuring a depth classification model to distinguish between a 3D subject and a realistic 2D rendering of a 3D subject comprises training the depth classification model using a first set of depth information and a second set of depth information, the first set of depth information provided by viewing a set of 3D subjects via a multi-camera apparatus, the second set of depth information provided by viewing a set of realistic 2D renderings of the set of 3D subjects via a multi-camera apparatus. ### Claim 19 (depends on 15) The computer system of claim 15, wherein the depth classification model comprises a convolutional neural network model. ### Claim 20 (depends on 15) The computer system of claim 15, wherein the image classification model comprises a convolutional neural network model configured to classify a subject using a set of image classification training data, a training data in the set of image classification training data comprising an image and a classification corresponding to the image.