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 .
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claim 6 is rejected under 35 U.S.C. 112(b), as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
Claim 6 is indefinite because the scope of the “texture material” comprising the “input control” is confusing/unclear, particularly the manner in which a texture material, which is created by the generation component recited in claim 1, further comprises an input control for obtaining the first media content. Furthermore, there is no grounding in the specification for these terms and the claim language itself does not adequately define these terms.
For the purpose of advancing prosecution, Examiner interprets “input control” as an element that controls obtaining the first media content in connection with the texture material and the texture material “comprising” the input control is interpreted as the input control being part of how the texture material is created and provided.
Claim 18, has similar limitations as of claim 6, therefore it is rejected under the same rationale as claim 6.
Appropriate correction is required.
Claim Rejections - 35 USC § 103
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.
Claims 1, 8-9, 13, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (US20230091423A1) and Nichol (Nichol A, Dhariwal P, Ramesh A, Shyam P, Mishkin P, McGrew B, Sutskever I, Chen M. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741. 2021 Dec 20.).
Regarding claim 1, Zheng teaches a method of effect editing, comprising: presenting a texture generation component based on a received texture creation request (Zheng; ¶0045, describes acquiring an editing request and calling the editing control (texture generation component) corresponding to the parameter item to be adjusted in response to the editing request and, Zheng; ¶0046 the editing/adjustment is directed toward a three-dimensional avatar (editing the three-dimensional avatar image is editing the texture). Zheng; ¶0041, further describes the editing control as a visual control provided on a visual editing page. This teaches presenting a texture generation component based on a received texture creation request.) obtaining at least one generation parameter via the texture generation component (Zheng; ¶0045-0046, describes the editing request (texture creation request) includes the adjusted parameter value obtained from the editing control (texture generation component) and the avatar is generated using the adjusted parameter value. This teaches obtaining at least one generation parameter via the texture generation component.)
However, Zheng does not disclose explicitly the at least one generation parameter comprises prompt information, creating a texture material based on the at least one generation parameter and generating a target effect based on the texture material.
Nichol teaches the at least one generation parameter comprising prompt information (Nichol; pg. 6 section 4.1, describes that for each noised image and corresponding text caption, the model conditions on the text by encoding it into tokens to feed to the model. This teaches the input for generation comprises text prompt information.) creating a texture material based on the at least one generation parameter (Nichol; pg. 7 section 5.1, describes the model generalizes to a wide variety of prompts and generates high-quality textures. This teaches creating texture based on the prompt information.) generating a target effect based on the texture material (Nichol; pg. 3 Fig. 2, describes/shows image inpainting where the model fills an erased region conditioned on the prompt to produce a realistic completion and, Nichol pg. 4 Fig. 3, describes/shows iterative generation of an output image from text prompts. This teaches generating a target effect based on created texture.)
It would have been obvious to one of ordinary skill in the art, before the effective filing data, to modify the parameter image editing and texture generation system of Zheng with the text prompt conditioning image generation of Nichol. The motivation for such a combination would have been to provide the benefit of easier and simpler user input and editing.
Claim 13, has similar limitations as of claim 1, therefore it is rejected under the same rationale as claim 1, except claim 13 further recites, “at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution”. Zheng teaches (Zheng; ¶0006) at least one processor and connected memory storing the executable instructions.
Claim 20, has similar limitations as of claim 1, therefore it is rejected under the same rationale as claim 1, except claim 20 further recites, a “non-transitory computer-readable storage medium having a computer program stored thereon”. Zheng teaches (Zheng; ¶0007) “a non-transitory computer-readable storage medium having computer instructions therein”.
Regarding claim 8, Zheng in view of Nichol teaches the method of claim 1, further comprising: presenting a preview interface based on a selection of a preview entry in the texture generation component (Zheng; ¶0035, describes obtaining the adjusted parameter value in response to a triggering operation of the editing control (texture generation component) for a parameter item to be adjusted and, Zheng; ¶0037, describes generation a preview image of the three-dimensional avatar and displaying the preview image (preview interface). Triggering operation of the editing control that initiates the generation and display of the preview is a selection of a preview entry in the texture generation component and the display that presents the preview image is a preview interface.) wherein the preview interface is configured to: obtain a third media content and a set of generation parameters (Zheng; ¶0035, describes obtaining the adjusted parameter value in response to the triggering operation of the editing control on the visual edit page and, Zheng; ¶0046 describes generating the three-dimensional avatar using the adjusted parameter value (set of generation parameters), three-dimensional model data, and target image data (third media content) related to the target image. This teaches the parameter values and media content are obtained through the same edit page where the preview is generated and displayed, so that the preview interface obtains the media content and the set of generation parameters used in generating the preview.)
Nichol teaches to provide a fourth media content generated based on the set of generation parameters and the third media content (Nichol; Fig. 2, describes text-conditional image inpainting where a region of an existing image is erased (third media content) and the model fills it in, conditioned on the prompt (generation parameter) to produce a realistic completion (fourth media content). In the combination, the preview interface of Zheng presents the content generated by the prompt-conditioned generation of Nichol from the obtained media and the set of generation parameters of the prompt information.)
It would have been obvious to one of ordinary skill in the art, before the effective filing data, to modify the preview generation and display of Zheng with the text prompt conditioning image generation of Nichol. The motivation for such a combination would have been to provide the benefit of allowing the user to view the generated result before finalizing.
Regarding claim 9, Zheng in view of Nichol teaches the method of claim 1, further comprising: applying the texture material to a second object in an effect to be edited (Nichol; Fig. 2, describes text-conditional inpainting where the generated content (texture material) is applied to an erased region of a depicted item (second object) of the existing image being edited. In the combination, this teaches applying the generated content to an object in the content being edited.)
It would have been obvious to one of ordinary skill in the art, before the effective filing data, to further modify the system of Zheng and Nichol with the content application of Nichol. The motivation for such a combination would have been to provide the benefit of enabling targeted editing.
Claims 2 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (US20230091423A1), Nichol (Nichol A, Dhariwal P, Ramesh A, Shyam P, Mishkin P, McGrew B, Sutskever I, Chen M. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741. 2021 Dec 20.), and Wang (US20250078386A1).
Regarding claim 2, Zheng in view of Nichol teaches the method of claim 1, including the texture generation component (Zheng; ¶0045, describes acquiring an editing request (texture creation request) and calling the editing control (texture generation component) corresponding to the parameter item to be adjust in response to the request and, Zheng; ¶0041, describes the editing control as a visual control on a visual edit page, where the editing operations include selecting.) and the at least one generation parameter, Zheng; ¶0045-0046, (see claim 1).
However, Zheng in view of Nichol does not disclose explicitly wherein the texture generation component comprises a style selection control configured to provide a set of candidate styles and the generation parameter further comprising a target style selected from the set of candidate styles.
Wang teaches a style selection control configured to provide a set of candidate styles and the at least one generation parameter further comprising a target style selected from the set of candidate styles. (Wang; Fig. 7 and ¶0092, describes a user interface that includes a display of different textures to be applied to the item, including a first, second, third, fourth, and fifth texture (set of candidate styles), and the second texture is selected (target style) in the user interface. Wang; ¶0041, describes the system displays controls in the user interface that are selectable (style selection control) to apply one or more different textures. This teaches a control providing a set of candidate texture options where a target option is selected to generate the output.)
It would have been obvious to one of ordinary skill in the art, before the effective filing data, to modify the system of Zheng in view of Nichol with the style/texture selection of Wang. The motivation for such a combination would have been to provide the benefit of improving user customization, selection, and control.
Claim 14, has similar limitations as of claim 2, therefore it is rejected under the same rationale as claim 2.
Claims 3 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (US20230091423A1), Nichol (Nichol A, Dhariwal P, Ramesh A, Shyam P, Mishkin P, McGrew B, Sutskever I, Chen M. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741. 2021 Dec 20.), Wang (US20250078386A1), and Song (US20230162320A1).
Regarding claim 3, Zheng in view of Nichol and Wang teaches the method of claim 2. However, Zheng in view of Nichol and Wang does not explicitly disclose receiving service information from a management device indicating the allowed set of candidate styles and providing the set of candidate styles based on the service information.
Song teaches receiving service information from a management device indicating the allowed set of candidate styles (Song; ¶0039, describes the server device (management device) includes the GAN generator, encoder and latent code blender of the generation service and, Song; ¶0040, describes the server device provides data and graphical content (service information) to the client through a network. The generation and stylization services come from the server, so the available styles are the ones sent from the server and received by the client device. The set of styles the server makes available is the allowed set of candidate styles.) providing the set of candidate styles in the texture generation component based on the service information (Song; ¶0039-0040, describes service information provided by a management device (see above). Wang; ¶0092, describes the user interface displaying different textures (set of candidate styles) for selection and, ¶0038, describes the functionality of the system is configurable in whole or in part via the network as part of a web service or cloud, teaching displaying (providing) the candidate set for the generation component from data (service information) received via the network. In the combination, the data received, as taught by Wang, is the service information of Song’s management device. The displayed sets are determined by the received service information, providing the set of candidate styles based on the service information.)
It would have been obvious to one of ordinary skill in the art, before the effective filing data, to modify the system of Zheng in view of Nichol and Wang with the server-hosted generation of Song. The motivation for such a combination would have been to provide the benefit of easily-controlled and simpler user selection.
Claim 15, has similar limitations as of claim 3, therefore it is rejected under the same rationale as claim 3.
Claims 4 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (US20230091423A1), Nichol (Nichol A, Dhariwal P, Ramesh A, Shyam P, Mishkin P, McGrew B, Sutskever I, Chen M. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741. 2021 Dec 20.), and Long (WO2023011146).
Regarding claim 4, Zheng in view of Nichol teaches the method of claim 1. Zheng; ¶0041, further describes the editing control (texture generation component) as a visual control on a visual edit page with editing forms including selecting, teaching a selection control for obtaining the generation parameter. However, Zheng in view of Nichol does not explicitly disclose the texture generation component comprises a dynamic effect selection control configured to provide a set of candidate dynamic effects or the generation parameter comprising a target dynamic effect selected from the set of candidate dynamic effects.
Long teaches a dynamic effect selection control configured to provide a set of candidate dynamic effects and a target dynamic effect selected from the set of candidate dynamic effects (Long; ¶0040, describes a video processing interface that displays sticker types containing multiple stickers (a set of candidate effects), where the user can swipe and select the target sticker (target effect selected from set), Long; ¶0039, describes the map can be a static map or dynamic map (target effects include dynamic), and, Long; ¶0086, describes when the target sticker is a dynamic sticker, the dynamic map is adjusted according to the movement of the target part. This teaches a control providing a set of candidate dynamic effects from which the user can select. In the combination, the selected dynamic effect is obtained by the texture generation component of Zheng in view of Nichol as a further generation parameter (with the prompt information) to generate the target effect.)
It would have been obvious to one of ordinary skill in the art, before the effective filing data, to modify the system of Zheng in view of Nichol with the dynamic effect selection of Long. The motivation for such a combination would have been to provide the benefit of improving user customization, selection, and control.
Claim 16, has similar limitations as of claim 4, therefore it is rejected under the same rationale as claim 4.
Claims 5-6 and 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (US20230091423A1), Nichol (Nichol A, Dhariwal P, Ramesh A, Shyam P, Mishkin P, McGrew B, Sutskever I, Chen M. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741. 2021 Dec 20.), Long (WO2023011146), and Krishnan (US11462195B2).
Regarding claim 5, Zheng in view of Nichol and Long teaches the method of claim 4 and the second media content generated based on the first media content and the prompt information (Nichol; Figure 2, describes image inpainting that is conditioned by text (prompt information), where a region of an existing image (first media content) is erased and the model fills it in based on the prompt and the image to produce a realistic completion (second media content). This teaches generating the second media content based on the first media content and the prompt information.)
However, Zheng in view of Nichol and Long does not disclose explicitly wherein the texture material comprises a transition between a first media content and a second media content according to the target dynamic effect.
Krishnan teaches wherein the texture material comprises a transition between a first media content and a second media content according to the target dynamic effect (Krishnan; ¶0024, describes converting first visual media item (first media content) to a second visual media item (second media content) according to a content-transition type determined from a set of content transition types. Krishnan; ¶0028, describes the content-transition types utilize a graphical effect transition that adds a graphical effect, such as an animation (dynamic effect), with transitioning from the first visual media item to the second visual media item. Krishnan; ¶0036, describes applying a content-transition type based on the content publisher’s preference or selection, teaching transitioning from a first content to a second content according to a selected transition effect, including an animated (dynamic) effect. In the combination, the first and second media content are the input content and the prompt-generated content of Nichol, the selected transition effect is the target dynamic effect selected from the selection control of Long (see claim 4).)
It would have been obvious to one of ordinary skill in the art, before the effective filing data, to modify the system of Zheng in view of Nichol and Long with the effect transition of Krishnan. The motivation for such a combination would have been to provide the benefit of smoother visuals and improving user customization, selection, and control.
Claim 17, has similar limitations as of claim 5, therefore it is rejected under the same rationale as claim 5.
Regarding claim 6, Zheng in view of Nichol, Long, and Krishnan teaches the method of claim 5, wherein the texture material further comprises an input control for obtaining the first media content (Nichol; section 4.3, describes modifying the model architecture to have additional input channels, a second set of RGB channels, and a mask channel, where the remaining portions of the existing image (first media content) are fed Into the model as conditioning information. This teaches an input for obtaining the first media content. Long; ¶0038, describes the pending video (first media content) can be uploaded by the user or collected in real time through the terminal device’s image acquisition device. In the combination, the first media content obtained as taught by Long is fed through the input path of Nichol for creating the texture material, so the input control is an element to create and provide the texture material and the texture material comprises the input control for obtaining the first media content.)
It would have been obvious to one of ordinary skill in the art, before the effective filing data, to further modify the system of Zheng in view of Nichol, Long, and Krishnan with the input pathway of Nichol and the content acquisition of Long. The motivation for such a combination would have been to provide the benefit allowing the user to use their own media, improving customization.
Claim 18, has similar limitations as of claim 6, therefore it is rejected under the same rationale as claim 6.
Claims 7 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (US20230091423A1), Nichol (Nichol A, Dhariwal P, Ramesh A, Shyam P, Mishkin P, McGrew B, Sutskever I, Chen M. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741. 2021 Dec 20.), Long (WO2023011146), and Kulasekara (Kulasekara, Geetha Udayangani, Buddhini Gayathri Jayatilleke, and Uma Coomaraswamy. "Designing interface for interactive multimedia: learner perceptions on the design features." Asian Association of Open Universities Journal 3.2 (2008): 83-98.).
Regarding claim 7, Zheng in view of Nichol and Long teaches the method of claim 4. However, Zheng in view of Nichol and Long does not explicitly disclose the texture generation component comprises a play control for configuring whether the target dynamic effect is automatically played.
Kulasekara teaches wherein the texture generation component comprises a play control for configuring whether the target dynamic effect is automatically played (Kulasekara; pg. 87 ¶2, describes animations incorporated with play, stop, and repeat buttons (play control) and, Kulasekara; pg. 88 ¶4, describes a control for the animations to “auto run” rather than by user operation. In the combination, the control sets an animation (dynamic effect) to play upon user operation or automatically via “auto run”, which is a play control for configuring whether the animation is played automatically.)
It would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify the system of Zheng in view of Nichol and Long with the animation play controls of Kulasekara. The motivation for such a combination would have been to provide the benefit of improved user control over the playback of an animated element.
Claim 19, has similar limitations as of claim 7, therefore it is rejected under the same rationale as claim 7.
Claims 10-11 are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (US20230091423A1), Nichol (Nichol A, Dhariwal P, Ramesh A, Shyam P, Mishkin P, McGrew B, Sutskever I, Chen M. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741. 2021 Dec 20.), and Guerrero (US11875446B2).
Regarding claim 10, Zheng in view of Nichol teaches the method of claim 1, including creating the texture material (Nichol; 5.1) and generating the target effect based on the texture material (Nichol; Figs. 2-3). However, Zheng in view of Nichol does not explicitly disclose generating the target effect comprises adding a target node corresponding to the texture material in a node graph of the target effect and generating the target effect based on an edit of the target node.
Guerrero teaches wherein generating a target effect based on the texture material comprises: adding a target node corresponding to the texture material in a node graph of the target effect (Guerrero; ¶0029, describes material graphs having nodes that represent operations on textures and describes manually combining (adding) filter nodes in a material graph to build material graphs that process textures and generate complex materials. In the combination, the added node performs an operation on the texture material created from the prompt information, teaching adding a target node, corresponding to the texture material, in a node graph of the target effect.) generating the target effect based on an edition of the target node (Guerrero; ¶0029, describes producing image maps through the material graph and controlling the output maps by editing parameters of individual nodes. Editing the parameters of the target node controls the generated material output; generating the target effect based on an edition of the target node.)
It would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify the system of Zheng in view of Nichol with the editable material node graph of Guerrero. The motivation for such a combination would have been to provide the benefit of improved control and user customization.
Regarding claim 11, Zheng in view of Nichol and Guerrero teaches the method of claim 10, wherein the edition of the target node comprises editing attribute information of the target node, and the attribute information comprises at least: an input texture of the target node (Guerrero; ¶0029, describes material graph nodes that perform operations on textures, with edges carrying information from node outputs to inputs of subsequent nodes, and describes controlling the output maps by editing parameters of individual nodes. Guerrero; Fig. 9 and ¶0156, describes the operator parameters are numerical values describing characteristics of the node and that a user selects the node and adjusts those parameters. The texture processing node has an input texture and editable parameters describing characteristics of the node and adjusting the parameters includes editing attribute information of the node comprising the input texture.)
It would have been obvious to one of ordinary skill in the art, before the effective filing date, to further modify the system of Zheng in view of Nichol and Guerrero with the attribute information editing of Guerrero. The motivation for such a combination would have been to provide the benefit of improved control and user customization.
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Zheng (US20230091423A1), Nichol (Nichol A, Dhariwal P, Ramesh A, Shyam P, Mishkin P, McGrew B, Sutskever I, Chen M. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741. 2021 Dec 20.), and Garbos (US20230419577A1).
Regarding claim 12, Zheng in view of Nichol method of claim 1, and Zheng further teaches a service that receives a request and returns a generated result (Zheng; ¶0028, describes a background management server receives a user request and generates data according to the request and feeds the data back to the terminal device.) However, Zheng in view Nichol does not explicitly disclose posting an effect file corresponding to the target effect, the effect file configured to invoke a service according to the at least one generation parameter to obtain a generated image, providing a corresponding target effect.
Garbos teaches posting an effect file corresponding to the target effect, wherein the effect file is configured to invoke a service according to the at least one generation parameter to obtain a generated image, thereby providing a corresponding target effect (Garbos; ABST, describes generating and storing an image file based on personalization information, storing the personalization information and metadata associated with the image file, and associating a link with the customized digital greeting card. When the link is referenced, the image file and personalization information are retrieved and used to generate textures and a digital animated version of the greeting card that presents a representation of the image file and is consistent with the personalization information. In the combination, the personalization information corresponds to the at least one generation parameter and the reference to the associated link requests the service of Zheng to obtain the generated image and provides the corresponding target effect. This teaches posting an image file corresponding to the customized target effect and configuring the file, through its link and personalization information, to generate the target effect based on the personalization information.)
It would have been obvious to one of ordinary skill in the art, before the effective filing date, to further modify the system of Zheng in view of Nichol with the stored image file and link-generation of Garbos. The motivation for such a combination would have been to provide the benefit of easier storing and sharing/recreation of the corresponding visual effect.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DAN F KALHORI whose telephone number is (571)272-5475. The examiner can normally be reached Mon-Fri 8:30-5:30 ET.
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, DEVONA E FAULK can be reached at (571) 272-7515. 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.
/DAN F KALHORI/Examiner, Art Unit 2618
/DEVONA E FAULK/Supervisory Patent Examiner, Art Unit 2618
Prosecution Insights