DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
2. The information disclosure statements (IDS) submitted on the following dates are in compliance with the provisions of 37 CFR 1.97 and are being considered by the Examiner: 12/17/2025.
Response to Amendment
3. Applicant’s amendments filed on 12/17/2025 have been entered. Claims 1, 5, 7, 9, 13, 17, and 19 have been amended. Claims 1-20 are pending in this application, with claims 1, 9 and 13 being independent.
Response to Arguments
4. Applicant's arguments filed on 12/17/2025, with respect to the 103 rejection have been fully considered but are moot in view of the new grounds of rejection.
Examiner notes that independent claims 1, 9 and 13 have been amended to include new limitation. Examiner finds these limitations to be unpatentable as can be found in below detail action.
In light of the current Office Action, the Examiner respectfully submits that independent claims 1, 9 and 13 are rejected in view of newly discovered reference(s) to Kale et al. (US-2025/0117126-A1) with the Provisional application No. 63/588,027, filed on Oct. 05, 2023.
Examiner notes that independent claims 1, 9 and 13 have been amended to include new
limitation. Examiner finds these limitations to be unpatentable as can be found in above detail
action.
5. On pages 10-11 of Applicant's Remarks, the Applicant argues that the dependent claims are not taught by the prior art, insomuch as they depend from claims that are not taught by the prior art. Examiner respectfully disagrees with these arguments, for the reasons discussed below.
Claim Rejections - 35 USC § 103
6. The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
7. Claims 1-2, 6, 9-10, 13-14 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Menges et al., (“Menges”) [US-2025/0086865-A1] with the Provisional application No. 63/582,141, filed on Sep. 12, 2023, in view with Kale et al., (“Kale”) [US-2025/0117126-A1] with the Provisional application No. 63/588,027, filed on Oct. 05, 2023,
further in view of Hu et al. [machine translation of CN-116612280-A with citation below, hereinafter “Hu”], still further in view of Meier et al., (“Meier”) [US-2017/0109929-A1]
Regarding claim 1, Menges discloses a drawing system (Menges- Figs. 2-3 and ¶0036-0038, at least disclose the generative design system 300) comprising:
a memory storing instructions that, when executed by a processor (Menges- Fig. 2 and ¶0040, at least disclose Various components of the environment 200 of FIG. 2 such as the remote server 210, the network 240, and the client device(s) 220 can each include one or more processors and a non-transitory computer-readable storage medium storing instructions that, when executed, cause the one or more processors to carry out the functions attributed to the respective devices), cause the processor to:
generate an image from a sketched stroke and text inputted to a learning model (Menges- Fig. 6 depicts an example embodiment of a text prompt input including recommended prompts for generating media content based on a sketch; Fig. 7 depicts a user interface for modifying media content based on a user's sketch drawn on an infinite canvas; Fig. 8 depicts a user interface for modifying an image based on a sketch; ¶0034, at least discloses States of the media content may include one or more labels indicating a time at which the content was generated, an order at which the content was generated (e.g., chronological order), which machine learning model(s) were used to generate the content, if and/or how a user modified the content, how the content was generated (e.g., with a sketch, user text prompt [a sketched stroke and text inputted], or a suggested prompt generated by the generative design system)]; ¶0042-0044, at least disclose States of the media content may include one or more labels indicating a time at which the content was generated, an order at which the content was generated (e.g., chronological order), which machine learning model(s) [learning model] were used to generate the content, if and/or how a user modified the content, how the content was generated (e.g., with a sketch, user text prompt [generate an image from a sketched stroke and text inputted], or a suggested prompt generated by the generative design system) […] The sketch fusion module 304 can modify media content based on a user's sketch drawn on an infinite canvas. A user may use a pen tool of the generative design system 300 to draw a sketch on the infinite canvas. The user may generate a first set of images using one or more generative models of the generative design system 300 […] The sketch fusion module 304 can use a machine learning model to identify one or more objects in a user's sketch […] Using the user's dropped location and the target object onto which the sketch is placed, the sketch fusion module 304 can then determine a text prompt for generating new images and/or generate a new image for image-to-image media content generation [generate an image from a sketched stroke and text inputted to a learning model]);
render an estimated sketch of the image (Menges- ¶0043, at least discloses The sketch fusion module 304 can modify media content based on a user's sketch drawn on an infinite canvas. A user may use a pen tool of the generative design system 300 to draw a sketch on the infinite canvas. The user may generate a first set of images using one or more generative models of the generative design system 300 […] The sketch fusion module 304 can determine the second set of images by identifying one or more objects of the sketch and using at least the identified one or more objects to generate the second set of images. The sketch fusion module 304 can use a machine learning model to identify one or more objects in a user's sketch […] modifying media content by dropping a sketch into the media content is depicted).
Menges does not explicitly disclose remix the text to generate forms of the image from randomized seeds associated with design parameters; segment the image to identify boundary information with a segmentation model and extract edge information from the image using an edge model; and render an estimated sketch of the image by computing an intersection between the boundary information and the edge information.
However, Kale discloses
remix the text to generate forms of the image from randomized seeds associated with design parameters (Kale- ¶0036-0037, at least disclose a user provides a text prompt [the text] describing image content to a user interface provided on a user device by the computing apparatus. The computing apparatus generates an image based on the text prompt and displays the image in a grid of the user interface. The user wants to generate a set of similar but randomized images, and so selects a “seed” variation mode from the user interface, in which a seed (e.g., a numerical image generation input parameter) will be a variation parameter […] The user clicks on the pull handle, drags the handle across seven sections of the grid, and releases the handle, thereby indicating, in an intuitive and user-friendly manner, that seven additional images should be generated [generate the image] based on the text prompt and seven random seeds [randomized seeds]. The computing apparatus generates seven additional images based on the text prompt and a corresponding random seed and displays the seven additional images in the grid; Fig. 2 and ¶0057, at least disclose the user provides a variation parameter (such as a seed) to the user interface, and indicates a number of variations (e.g., a number of images that differ by each other with respect to the variation parameter). The media content system generates a set of variation inputs (e.g., a set of random seeds) based on the variation parameter [randomized seeds associated with design parameters]. The media content system generates a set of images including the number of different images based on the original image and the corresponding set of variation inputs and displays the set of images to the user on the design board; Fig. 8 and ¶0109, at least disclose at operation 805, a user provides an input (such as a text prompt) describing content to be included in a generated image. For example, a user may provide the prompt “a person playing with a cat” [text]. In some examples, the set of variation inputs is provided as guidance. In some examples, guidance can be provided in a form other than text, such as via an image, a sketch, a layout [forms of the image], etc.; Figs. 13-14 and ¶0130-0132, at least disclose a user has dragged variation handle 1325 to a new position on design board 1300 (e.g., design board 1200). Additional tile count 1320 (7) is shown on a cord of variation handle 1325, indicating a number of additional tiles (including additional tile 1315) of design board 1300 that will be populated with additional images generated based on the image generation parameters [design parameters] for image 1310 (e.g., image 1205) with corresponding modified seeds. As shown in FIG. 13 , each additional tile includes text identifying a randomly chosen seed (for example, via random number generation) that each corresponding additional image will be generated based on [remix the text to generate forms of the image from randomized seeds]. In some cases, a seed is an input to a diffusion model that determines an appearance of a generated image, such that two images generated by a same diffusion model with a same number of iterations based on a same seed will be identical […] design board 1400 (e.g., design board 1300) displays additional images (including additional image 1410) generated based on image 1405 and the seeds of FIG. 13; Figs. 25 and ¶0166-0167, at least disclose a set of text prompts represented by text prompt preset representation 2505 are used to respectively populate a set of tiles (including tile 2515) by dragging text prompt preset representation 2505 onto an empty tile of design board 2500 […] each of the tiles will include an image generated or retrieved based on the corresponding text prompt [remix the text to generate forms of the image]);
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Menges to incorporate the teachings of Kale, and apply the dragging text prompt and the randomly chosen seed into generating an image from a sketched stroke and text inputted, as toughed by Menges, in order to generate an image from a sketched stroke and text inputted to a learning model, and remix the text to generate forms of the image from randomized seeds associated with design parameters.
Doing so would intuitively obtaining a set of media content items and displaying the set of media content items in a user-friendly manner.
Kale further discloses
generate an image from a text inputted to a learning model (Kale- ¶0027, at least discloses Media such as images, audio, video, and text can be generated and modified both algorithmically and by using machine learning. In an example, a user can generate an image by providing a text prompt describing content of an image to a machine learning model, and the machine learning model can generate the image based on the text prompt. In another example, a user can adjust an input parameter with respect to an existing image, and an algorithm can modify the existing image based on the adjusted input parameter).
The does not explicitly disclose, but Hu discloses
segment the image to identify boundary information with a segmentation model
(Hu- ¶0033-0036, at least disclose the advanced vehicle segmentation model [a segmentation model] is obtained by training the initial segmentation network using the vehicle mask of the vehicle sample map […] extracting the image within the first region of interest of the preliminary segmentation map to obtain the first vehicle mask of the preliminary segmentation map includes: Extract the image [segment the image] within the first area of interest of the preliminary segmentation map to obtain the initial vehicle mask of the preliminary segmentation map; Extract the contours [identify boundary information] of the initial vehicle mask, and expand the extracted contours to obtain an edge-enlarged contour image; The first vehicle mask is determined according to the image of the area where the minimum circumscribed rectangle of the outline image is located) and extract edge information from the image using an edge model (Hu- ¶0039, at least discloses the edge enhancement module [edge model] is used to extract edge features [edge information] in the vehicle sample image and enhance the edge features to obtain the corresponding edge enhancement weight of each pixel; ¶0044, at least discloses extract the edge features [extract edge information] in the vehicle sample map, enhance the edge features, and obtain each pixel For the corresponding edge enhancement weight, the loss value corresponding to each pixel is weighted according to the edge enhancement weight to obtain the edge enhancement loss value. That is, by adjusting the weight of the edge pixels, the initial segmentation network pays more attention to the edge characteristics of the vehicle, so based on the edge […] the vehicle segmentation model obtained by iterative model training can accurately identify the edge features of the vehicle, thereby improving the accuracy of the vehicle segmentation results obtained using the vehicle segmentation model; ¶0068-0069, at least discloses Extract edge features in the vehicle sample image and enhance the edge features to obtain the edge enhancement weight corresponding to each pixel […] the computer device extracts edge features in the vehicle sample map to obtain an edge map; and enhances the edge features in the edge map to obtain edge enhancement weights corresponding to each pixel; ¶0109, at least discloses Extract edges from the vehicle annotation map 204 and enhance the extracted edge features to obtain an edge weight map 306); and
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Menges/Kale to incorporate the teachings of Hu, and apply the segmentation map and extracting the contours and extracting edge features into generating an image from a sketched stroke and text inputted, as toughed by Menges/Kale, in order to segment the image to identify boundary information with a segmentation model and extract edge information from the image using an edge model.
Doing so would provide improve the accuracy of vehicle segmentation results.
The prior art does not explicitly disclose, but Meier discloses
render an estimated sketch of the image by computing an intersection between the boundary information and the edge information (Meier- ¶0104-0105, at least disclose Assuming a floor plane 17 with walls 18 in the scenery 10 according to FIG. 2A, and once these planes are identified, a wizard can identify all objects breaking through the boundary between floor and wall. For this purpose, a surface segmentation can either previously be carried out and the surfaces can be intersected with the straight lines 19. Alternatively, there can take place a gradient observation along the straight lines 19, and deviating minority units in combination with similar colors on both planes be employed as growing seeds for segmentations […] In FIG. 2B those places are marked with reference sign 16 where objects of the real environment intersect the straight lines 19, i.e. the transition between wall and floor planes; ¶0126, at least discloses 3D edge information can be used in order for intersections of object boundaries or of other edges to be correctly computed).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Menges/Hu/Kale to incorporate the teachings of Meier, and apply the edge information can be used in order for intersections of object boundaries to be correctly computed into Menges/Hu/Kale’s teachings in order to render an estimated sketch of the image by computing an intersection between the boundary information and the edge information.
Doing so would remove spurious objects by employing image segments.
Regarding claim 2, Menges in view of Kale, Hu and Meier, discloses the drawing system of claim 1, and further discloses wherein the instructions to segment the image further include instructions to:
estimate a segmentation map by the segmentation model (Hu- ¶0031, at least discloses input the first vehicle mask into the advanced vehicle segmentation model to obtain a segmentation map of the first vehicle mask, and use the segmentation map of the first vehicle mask as an advanced segmentation map of the vehicle image); and
draw natural borders for colored parts defined by the segmentation map to derive the boundary information (Hu- ¶0076, at least discloses when the vehicle segmentation model is used to segment vehicle images into vehicle parts, the vehicle annotation map uses different colors to distinguish different vehicle parts; ¶0096-0097, at least discloses extracting the image within the first region of interest of the preliminary segmentation map to obtain the first vehicle mask of the preliminary segmentation map includes: extracting the image within the first region of interest of the preliminary segmentation map to obtain the preliminary segmentation. The initial vehicle mask of the image; perform contour extraction on the initial vehicle mask, and expand the extracted contour to obtain an edge--enlarged contour image; determine the first vehicle mask based on the image of the area where the minimum circumscribed rectangle of the contour image is located […] performs contour extraction on the initial vehicle mask to obtain the initial contour image).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Menges/Meier/Kale to incorporate the teachings of Hu, and apply the different colors and the initial contour image into Menges/Meier/Kale’s teachings in order to draw natural borders for colored parts defined by the segmentation map to derive the boundary information.
The same motivation that was utilized in the rejection of claim 1 applies equally to this claim.
Regarding claim 6, Menges in view of Kale, Hu and Meier, discloses the drawing system of claim 1 further including instructions to:
underlay the estimated sketch within a canvas on an interface (Menges- Fig. 7 depicts a user interface for modifying media content based on a user's sketch drawn on an infinite canvas; ¶0070, at least discloses a user interface 700 for modifying media content based on a user's sketch drawn on an infinite canvas […] A user may use a pen tool 702 to draw a sketch 704 of a dog on the infinite canvas. The user may generate a first set 708 of images of a park using the generative design system 300. The user may use the cursor tool to drag 706 the sketch 704 into one of the images of the first set 708 of images and in response, the generative design system 300 can create a second set 710 of images that combine the sketch 704 and the image into which it was dropped);
modify the estimated sketch within the interface (Menges- ¶0070, at least discloses a user interface 700 for modifying media content based on a user's sketch drawn on an infinite canvas […] The generative design system 300 may modify (e.g., augment) the instructions used to generate the first set 708 of images using the one or more identified objects. For example, after identifying a dog is in the sketch 704, the generative design system 300 may add a keyword “dog” to the text prompt of “park” used to generate the first set 708 of images.); and
receive by the learning model the estimated sketch as a feedback input (Menges- ¶0070, at least discloses The generative design system 300 can use machine learning models to identify one or more objects in a user's sketch. The generative design system 300 may modify (e.g., augment) the instructions used to generate the first set 708 of images using the one or more identified objects. For example, after identifying a dog is in the sketch 704, the generative design system 300 may add a keyword “dog” to the text prompt of “park” used to generate the first set 708 of images).
Regarding claims 9-10, all claim limitations are set forth as claims 1-2 in a non-transitory computer-readable medium comprising instructions that when executed by a processor cause the processor and rejected as per discussion for claims 1-2.
Regarding claim 9, Menges discloses a non-transitory computer-readable medium comprising: instructions that when executed by a processor (Menges- Fig. 2 and ¶0040, at least disclose Various components of the environment 200 of FIG. 2 such as the remote server 210, the network 240, and the client device(s) 220 can each include one or more processors and a non-transitory computer-readable storage medium storing instructions that, when executed, cause the one or more processors to carry out the functions attributed to the respective devices) cause the processor to perform the functions of claim 1.
The methods of claims 13-14 and 18 are similar in scope to the functions performed by the drawing system of claims 1-2 and 6 and therefore claims 13-14 and 18 are rejected under the same rationale.
8. Claims 4, 12, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Menges in view of Kale, further in view of Hu, further in view of Meier, still further in view of Chen et al., (“Chen”) [US-2020/0334793-A1]
Regarding claim 4, Menges in view of Kale, Hu and Meier, discloses the drawing system of claim 2, and does not explicitly disclose, but Chen disclose wherein the natural borders separate the colored parts according to classifications identified by the segmentation map (Chen- ¶0011, at least discloses detect a contour edge of a shooting subject in the foreground region; ¶0050, at least discloses the electronic device may divide an image to be processed into a foreground region and a background region by use of a pre-trained classification model, detect a contour edge of a shooting subject (i.e., a shooting target, for example, a person, an object and a scenery) in the foreground region and perform blurring on the background of the image to be processed according to the contour edge of the shooting subject. For example, by taking the contour edge of the shooting subject as a boundary, a region other than the shooting subject may be blurred, to highlight the shooting subject; ¶0058, at least discloses The semantic tag represents the object class of the corresponding pixel. The pixels with the same semantic tag are marked in the same color to obtain the semantic segmentation graph. For example, different object classes may be represented with different colors, and the semantic segmentation graph is generated according to the semantic tags. In the semantic segmentation graph, different segmented regions are represented with different colors, and different segmented regions represent different objects. For example, a red segmented region represents a vehicle, a green region represents a ground and a blue segmented region represents a person).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Menges/Kale/Hu/Meier to incorporate the teachings of Chen, and apply the different segmented regions are represented with different colors into Menges/Kale/Hu/Meier’s teachings in order the natural borders separate the colored parts according to classifications identified by the segmentation map.
Doing so would improve blurring accuracy and improve a blurring effect.
Regarding claim 12, all claim limitations are set forth as claim 4 in a non-transitory computer-readable medium comprising instructions that when executed by a processor cause the processor and rejected as per discussion for claim 4
The method of claim 16 is similar in scope to the functions performed by the drawing system of claim 4 and therefore claim 16 is rejected under the same rationale.
9. Claims 5 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Menges in view of Kale, further in view of Hu, further in view of Meier, still further in view of Willkie, (“Willkie”) [US-2023/0186569-A1]
Regarding claim 5, Menges in view of Kale, Hu and Meier, discloses the drawing system of claim 2, and does not explicitly disclose, but Willkie discloses wherein the edge information includes soft edges about the image, wherein the soft edges include structural lines having varying thicknesses, opacities, and transparency levels (Willkie- Fig. 2 and ¶0083, at least disclose the XR system 100 can render an outline around the surface plane 218 as a content placement indicator, render the surface plane 218 with a visual pattern (e.g., with a color, gradient, shading, transparency, fill, line, text, shadow, reflection, glow, soft edges, virtual object, etc.) as a content placement indicator, render a visual indicator (e.g., an arrow, text, animation, image, visual effect, etc.) as a content placement indicator, and/or can provide any other rendering or visualization that can indicate the surface plane 218 as available).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Menges/Kale/Hu/Meier to incorporate the teachings of Willkie, and apply the soft edges into Menges/Kale/Hu/Meier’s teachings in order the edge information includes soft edges about the image, wherein the soft edges include structural lines having varying thicknesses, opacities, and transparency levels.
Doing so would provide a user of the XR device a realistic XR experience.
The method of claim 17 is similar in scope to the functions performed by the drawing system of claim 5 and therefore claim 17 is rejected under the same rationale.
10. Claims 7 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Menges in view of Kale, further in view of Hu, further in view of Meier, still further in view of Spiegel et al., (“Spiegel”) [US-2024/0249318-A1]
Regarding claim 7, Menges in view of Kale, Hu and Meier, discloses the drawing system of claim 1, and does not explicitly disclose, but Spiegel discloses wherein the design parameters are associated with one of a body line, an exterior contour, scenery information, a product type, a product feel, and a product perception (Spiegel- ¶0107, at least discloses the LLM 338 is trained on the latest products being offered by advertisers on the interaction system 100 and offers product information on those products in response to requests by a user for the newest model of particular product categories; ¶0114, at least discloses The chatbot system 300 analyzes the received landing page/application using natural language processing techniques to extract useful details like product features, visual assets, and branding elements).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Menges/Kale/Hu/Meier to incorporate the teachings of Spiegel, and apply the large language model and the product categories into Menges/Kale/Hu/Meier’s teachings in order the design parameters are associated with one of a body line, an exterior contour, scenery information, a product type, a product feel, and a product perception.
Doing so would provide a way for users to interact with other users with similar interests.
11. Claims 8 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Menges in view of Kale, further in view of Hu, further in view of Meier, still further in view of Spiegel et al., (“Spiegel”) [US-2024/0249318-A1], still further in view of Harpavat et al., (“Harpavat”) [US-2025/0117990-A1]
Regarding claim 8, Menges in view of Kale, Hu and Meier, discloses the drawing system of claim 1, and further discloses wherein the instructions to generate the image from the sketched stroke (see Claim 1 rejection for detailed analysis) further include instructions to:
process the text by a large language model (LLM) of the learning model to output design ideas (Menges- ¶0062, at least discloses The generative design system 300 may generate a text prompt using the determined attributes and a text generation model (e.g., a large language model). For example, a user may use a cursor tool to outline a dog within an image of a dog in a park; ¶0066, at least discloses the generative design system 300 may use prompts previously provided by the user or multiple users to train a model (e.g., large language models or other suitable machine learning models) to determine prompts 406 to recommend […] The generative design system 300 may apply a machine learning model to determine one or more text prompts that a user is likely to select), and
The prior art does not explicitly disclose the text includes a product category and a design concept associated with the design ideas; and form the image by a control network (controlnet) of the learning model according to the design ideas and the sketched stroke.
However, Spiegel discloses
wherein the text includes a product category (Spiegel- ¶0030, at least discloses textual components of ads are used to finetune the responses of an LLM, thus conditioning the responses of the large language model; ¶0035, at least discloses the chatbot system generates a response using the prompt and a large language model; ¶0107, at least discloses the LLM 338 is trained on the latest products being offered by advertisers on the interaction system 100 and offers product information on those products in response to requests by a user for the newest model of particular product categories; ¶0116-0117, at least disclose the chatbot system 300 receives additional context like product specifications, product catalogs, and other relevant assets from the advertiser in operation 316 […] The chatbot system 300 analyzes the received product details and catalogs using natural language processing to identify key attributes and messaging […] The chosen creative direction steers the chatbot system 300 to generate ads with designs, layouts, and copy that help the advertiser's content resonate with their target audience); and
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Menges/Kale/Hu/Meier to incorporate the teachings of Spiegel, and apply the large language model and the product categories into Menges/Kale/Hu/Meier’s teachings in order to process the text by a large language model (LLM) of the learning model to output design ideas, wherein the text includes a product category.
Doing so would provide a way for users to interact with other users with similar interests.
The prior art does not explicitly disclose, but Harpavat discloses
form the image by a control network (controlnet) of the learning model according to the design ideas and the sketched stroke (Harpavat- ¶0002, at least disclose scribbles can range from rudimentary doodles capturing the essence of an idea to more elaborate sketches outlining preliminary design concepts. In the area of image processing, scribbles can act as the initial constructs from which digital graphics and designs are manually formulated and provide a direct and engaging method to capture and refine creative visions, thereby fostering innovation and efficiency in design workflows; ¶0101, at least disclose a ControlNet is a neural network architecture that allows guiding image generation via Diffusion Models, through user-specified control signals. It creates a trainable copy of the U-Net encoder, and only fine-tuning this copy, freezing the original U-Net. […] Since the original U-Net is not affected, and a new encoder copy learns to follow the control signals, ControlNet allows efficient fine-tuning of large diffusion models for such specific tasks, without losing the generative power of the base model. Accordingly, a sketch encoder such as a ControlNet provides scribble as the control signal for guiding image generation using an optional text prompt; Fig. 9 and ¶0116, at least disclose the image generation process using a modified ControlNet architecture is directed by guidance signals including sketch input 920 and text prompt 905. Text prompt 905 provides an additional layer of semantic context or directives for the image generation process, enhancing the specificity and relevance of the generated image to the user's intent. Sketch input 920 provides structural or stylistic guidance as the primary control signal).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Menges/Kale/Hu/Meier/Spiegel to incorporate the teachings of Harpavat, and apply the ControlNet and the design concepts into Menges/Hu/Meier/Spiegel’s teachings in order to process the text by a large language model (LLM) of the learning model to output design ideas, wherein the text includes a product category and a design concept associated with the design ideas; and form the image by a control network ( controlnet) of the learning model according to the design ideas and the sketched stroke.
Doing so would provide a direct and engaging method to capture and refine creative visions, thereby fostering innovation and efficiency in design workflows.
The methods of claim 20 is similar in scope to the functions performed by the drawing system of claim 8 and therefore claim 20 is rejected under the same rationale.
Allowable Subject Matter
12. Claims 3, 11 and 15 are objected to as being dependent upon a rejected base
claim, but would be allowable if rewritten in independent form including all of the
limitations of the base claim and any intervening claims.
13. The following is a statement of reasons for the indication of allowable subject
matter:
Regarding Claim 3, the combination of prior arts teaches the method of Claim 1.
However in the context of claim 1, 2 and 3 as a whole, the combination of prior arts does
not teach remove texture and redundant lines for locating the natural borders according to the intersection between the boundary information and the edge information, wherein the intersection are areas within the image having visual data that is similar. Therefore, Claim 3 in the context of claims 1, 2 as a whole does comprise allowable subject matter.
Regarding Claim 11, the combination of prior arts teaches the method of Claim 9.
However in the context of claim 9, 10 and 11 as a whole, the combination of prior arts does
not teach remove texture and redundant lines for locating the natural borders according to the intersection between the boundary information and the edge information, wherein the intersection are areas within the image having visual data that is similar. Therefore, Claim 11 in the context of claims 9, 10 as a whole does comprise allowable subject matter.
Regarding Claim 15, the combination of prior arts teaches the method of Claim 13.
However in the context of claim 13, 14 and 15 as a whole, the combination of prior arts does
not teach removing texture and redundant lines for locating the natural borders according to the intersection between the boundary information and the edge information, wherein the intersection are areas within the image having visual data that is similar. Therefore, Claim 15 in the context of claims 13, 14 as a whole does comprise allowable subject matter.
Conclusion
14. Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
15. Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL LE whose telephone number is (571)272-5330. The examiner can normally be reached 9am-5pm.
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, Kent Chang can be reached at (571) 272-7667. 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.
/MICHAEL LE/Primary Examiner, Art Unit 2614