DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
This office action is in response to amendments filed on 03/27/2026.
Specification
The title of the invention is not descriptive. A new title is required that is clearly indicative of the invention to which the claims are directed. Applicant should indicate the machine learning element for graphical creation in gaming.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-6 and 21-34 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Liu et al. (US Pub. No. 2023/0066897 A1 hereinafter referred to as Liu).
As per claims 1, 26, and 34, Liu teaches a method, computer-readable medium, and system comprising: one or more processors, and one or more computer-readable media that store instructions which, when executed by the one or more processors, cause the one or more processors to perform operations (paragraph [0004]) comprising: obtaining a set of initial graphics assets for a video game (paragraphs [0035] and [0037] “and process these inputs to generate 3D shape data for a portion of a video game building exterior in accordance with the conditioning input” image generation for a video game), each graphics asset comprising at least initial model data for an object (paragraph [0034] “the image segmentation model 203 comprises a machine-learning model, the image segmentation model 203 is trained using a plurality of training examples. Each training example comprises a training input and a target output. The training input of a training example comprises an image displaying a view of an exterior of a building (which may be a real building, or a video game building). The target output of a training example comprises a segmented image for the training input that is divided into a plurality of segments that each correspond to a particular class.” Machine learning model trained on a plurality of images, such as buildings, including video game building images); obtaining text data from one or more sources (paragraph [0047] “The text data specifies style information 304 and structural information 303 for the building exterior, which is extracted by the semantic analysis model 302. An example of text data 301 may be "Generate a modem style building with 8 floors using simple glass windows". The text data 301 may be provided directly by a user input, or may otherwise be determined. For example, the user may be guided by a user interface and asked a series of questions, e.g. ("What style do you want the building to be?", "How many floors do you want the building to have?", etc.), and the corresponding answers may be used to determine the text data 301.” Text prompts are received from a user); providing at least some of the text data to a machine learning model (paragraphs [0048]-[0049] text data is processed to determine attributes as style information, paragraph [0052] processed by a style encoder, and paragraphs [0054] and [0058]-[0060] with style encoding received by the asset generator model and building exterior generator to generate the 3D object); receiving, from the machine learning model, one or more images from the machine learning model (Fig. 5 and paragraphs [0072] and [0077] 3D image is generated); and modifying the set of initial graphics assets for the video game based at least on the received one or more of the images (paragraphs [0077]-[0078] image is added to the game and displayed thus modifying the initial set of graphic assets for the game).
As per claims 2 and 27, Liu teaches a method and system wherein the machine learning model comprises a text-to-image model that is trained to generate based at least on a natural language description (paragraph [0047] "Generate a modem style building with 8 floors using simple glass windows" is an example text) indicated by the text data (paragraphs [0048]-[0049] text data is processed to determine attributes as style information, paragraph [0052] processed by a style encoder, and paragraphs [0054] and [0058]-[0060] with style encoding received by the asset generator model and building exterior generator to generate the 3D object).
As per claims 3 and 28, Liu teaches a method and system wherein of modifying the set of initial graphics assets comprises associating a respective image with initial model data for a given object for using the respective image as a texture for the initial model data (paragraphs [0028] and [0034] model is trained on initial images and generates assets which include texture data based on the training).
As per claims 4 and 29, Liu teaches a method and system wherein modifying the set of initial graphics assets comprises modifying initial texture data for a given object based at least on a respective image to obtain modified texture data for the given object (paragraphs [0028] and [0034] model is trained on initial images and generates assets which include texture data based on the training).
As per claims 5 and 30, Liu teaches a method and system wherein generating comprises generating one or more respective instances of model data each associated with a respective image of the one or more respective images (paragraph [0034]).
As per claims 6 and 31, Liu teaches a method and system wherein the machine learning model comprises a text-to-image model that is configured to generate images based at least on the text data (paragraphs [0022] and [0034] model is trained on images with the images including labels such as windows or other features and those labels are then associated with text prompts paragraph [0047]).
As per claims 21 and 32, Liu teaches a method and system comprising: inputting at least some of the plurality of respective images to a second machine learning model (paragraphs [0054] and [0058]-[0060] with style encoding received by the asset generator model and building exterior generator with examiner recognizing that both are trained on image data with the asset generator being a machine learning model that generates the assets and the building exterior using the assets to generate the building. Therefore two models are present.); and generating the one or more respective instances of model data based at least on some of the plurality of respective images using the second machine learning model, the second machine learning model having been trained using labelled training data comprising images of objects and labels corresponding to model data for the objects to learn to map an image including an object to a label indicative of model data for that object (paragraphs [0054] and [0058]-[0060] with style encoding received by the asset generator model and building exterior generator with examiner recognizing that both are trained on image data with the asset generator being a machine learning model that generates the assets and the building exterior using the assets to generate the building. Therefore two models are present.).
As per claims 22 and 33, Liu teaches a method and system comprising: providing at least some of the set of initial graphics assets for the video game for input to the machine learning model (paragraph [0034] “the image segmentation model 203 comprises a machine-learning model, the image segmentation model 203 is trained using a plurality of training examples. Each training example comprises a training input and a target output. The training input of a training example comprises an image displaying a view of an exterior of a building (which may be a real building, or a video game building). The target output of a training example comprises a segmented image for the training input that is divided into a plurality of segments that each correspond to a particular class.” Machine learning model trained on a plurality of images, such as buildings, including using video game assets).
As per claim 23, Liu teaches a method comprising: mapping at least some of the respective images to at least some of the initial graphics assets using the machine learning model (paragraphs [0077]-[0078] image is added to the game and displayed thus modifying the initial set of graphic assets for the game including the building object itself which now has a visual appearance).
As per claim 24, Liu teaches a method wherein: modifying the set of initial graphics assets for the video game comprises one or more of: adding one or more graphics assets to the set of initial graphics assets (paragraphs [0077]-[0078] image is added to the game and displayed thus modifying the initial set of graphic assets for the game including the building object itself which now has a visual appearance); or modifying initial texture data for one or more of the initial graphics assets in dependence on one or more of the respective images (paragraphs [0077]-[0078] image is added to the game and displayed thus modifying the initial set of graphic assets for the game including the building object itself which now has a visual appearance).
As per claim 25, Liu teaches a method wherein: each of the one or more respective images has a same image style (paragraphs [0012] and [0077]-[0078] image is generated based on style meaning that the images being generated for a given style would have the same style).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Du et al. (US Pub. No. 2023/0196117 A1) broadly discussed conventional machine learning such as supervised and unsupervised (paragraph [0003]).
Han et al. (US Pub. No. 2023/0169075 A1) broadly discusses transformer neural network of the conventional technique in order to create natural language query and scheme to translate information for use by the system (paragraphs [0088]-[0090]).
Starke et al. (US Pub. No. 2023/0177755 A1) teaches a method for predicting facial expressions for a character wherein a second machine learning model is applied to generate facial poses for a second virtual character.
Rong et al. (US Pub. No. 2022/0165043 A1) teaches a "machine-learned refinement model processes the initial augmented image to add one or more of texture correction, color correction, or contrast correction to a border between the at least one of the one or more real world images and the simulated object" (claim 29).
Ji et al. (US Pub. No. 2022/0121920 A1) teaches the element of machine learning including conventional methods.
Banasal et al. (US Pub. No. 2021/0291046 A1) teaches a second machine learning model which the first machine learning model is derived.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JUSTIN L MYHR whose telephone number is (571)270-7847. The examiner can normally be reached 10AM-6PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Dmitry Suhol can be reached at (571) 272-4430. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/JUSTIN L MYHR/ Primary Examiner, Art Unit 3715 6/17/2026
Prosecution Insights