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 .
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claim 1-3, 6-13, 16-19, 20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claim 1, 2, 5, 6-12, 5, 6, 17-18, 11, 20 of U.S. Patent No.12223611 respectively. Although the claims at issue are not identical, they are not patentably distinct from each other because they are obvious variants of one another.
Claims 4-5 rejected on the ground of nonstatutory double patenting as being unpatentable over claim 1 of U.S. Patent No. 12223611 in view of Karras.
Regarding claim 4, U.S. Patent No. 12223611 teaches:
The computer-implemented method of claim 1,
However, U.S. Patent No. 12223611 does not, but Karras teaches:
wherein sampling from the distribution comprises generating the additional style code based on an aggregation of two or more style codes selected from the plurality of style codes. (Karras [0043]-[0044], “FIG. 2A illustrates a block diagram of the mapping neural network 110 shown in FIG. 1A, in accordance with an embodiment. A distribution of the training data may be missing a combination of attributes, such as, children wearing glasses. A distribution of the factors of variation in the combination of glasses and age becomes more linear in the intermediate latent space W compared with the latent space custom-character. In an embodiment, the mapping neural network 110 includes a normalization layer 205 and multiple fully-connected layers 210. In an embodiment, eight fully-connected layers 210 are coupled in sequence to produce the intermediate latent code. Parameters (e.g., weights) of the mapping neural network 110 are learned during training and the parameters are used to process the input latent codes when the style-based generator system 100 is deployed to generate the output data. In an embodiment, the mapping neural network 110 generates one or more intermediate latent codes that are used by the synthesis neural network 140 at a later time to generate the output data.”)
U.S. Patent No. 12223611 teaches generating a style code. Karras teaches a specific method of generating a style code.
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to have combined the teachings of U.S. Patent No. 12223611 with the specific teachings of Karras to generate a style code with reasonable expectation of success.
Regarding claim 5, U.S. Patent No. 12223611 in view of Karras teaches:
The computer-implemented method of claim 4, wherein the aggregation comprises a weighted average. (Karras [0038], “In the case of one dataset of human faces (e.g., FFHQ, Flickr-Faces-HQ), the point represents a sort of an average face (ψ=0).” The combination of claim 4 above is incorporated here.)
Claim 14 and 15 recite similar limitations of claim 4-5 respectively, thus are rejected accordingly.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claim(s) 1-2, 4-7, 9-12, 14-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chandran et al. (US 2022/0156987 A1) in view of Karras et al. (US 2020/0151559 A1) and further in view of Hwang et al. (US 2014/0192045 A1).
Regarding claim 1, Chandran teaches:
A computer-implemented method for performing style transfer, the method comprising: executing a first trained machine learning model based on the additional style code to generate an output three-dimensional (3D) shape having one or more style-based attributes associated with the additional style code and one or more content-based attributes associated with an object; ([0046], “After training engine 122 has completed training of style transfer model 200, execution engine 124 may execute the trained style transfer model 200 to produce style transfer result 236 from a new content sample 226 and style sample 230. For example, execution engine 124 may input a content image (e.g., an image of a face) and a style image (e.g., an artistic depiction of an object or scene that does not have to be a face) into style transfer model 200 and obtain, as output from style transfer model 200,” [0026]) and
However, Chandran does not, but Karras teach:
determining a distribution of a plurality of style codes; ([0043]-[0044], “FIG. 2A illustrates a block diagram of the mapping neural network 110 shown in FIG. 1A, in accordance with an embodiment. A distribution of the training data may be missing a combination of attributes, such as, children wearing glasses. A distribution of the factors of variation in the combination of glasses and age becomes more linear in the intermediate latent space W compared with the latent space custom-character. In an embodiment, the mapping neural network 110 includes a normalization layer 205 and multiple fully-connected layers 210. In an embodiment, eight fully-connected layers 210 are coupled in sequence to produce the intermediate latent code. Parameters (e.g., weights) of the mapping neural network 110 are learned during training and the parameters are used to process the input latent codes when the style-based generator system 100 is deployed to generate the output data. In an embodiment, the mapping neural network 110 generates one or more intermediate latent codes that are used by the synthesis neural network 140 at a later time to generate the output data.”)
sampling from the distribution to generate a additional style code; ([0040], “At step 160, the intermediate latent code is converted into a first style signal by the style conversion unit 115.”)
Chandran teaches performing style transferring based on input style. Karras teaches a specific method of how to generate a style.
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to have combined the teachings of Chandran with the specific teachings of Karras to generate a style transferring based on user’s desired style.
However, Chandran in view of Karras does not, but Hwang teaches
and generating a 3D model of the object based on the output 3D shape ([0050], “. Also, the 3D unique face model generation unit 203 may generate a 3D unique face model based on the generated shape and texture of the unique face.”)
Chandran in view of Karras teaches generating a 3D shape with desired style. Hwang further teaches generating 3D model based on the 3D shape.
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to have combined the teachings of Chandran in view of Karras with the specific teachings of Hwang to generate a 3D model of an object with desired style.
Regarding claim 2, Chandran in view of Karras and Hwang teaches:
The computer-implemented method of claim 1, wherein determining the distribution comprises training a machine learning model based on one or more losses associated with the plurality of style codes.( Karras [0045], “There are many attributes in human portraits that can be regarded as stochastic, such as the exact placement of hairs, stubble, freckles, or skin pores. Any of these can be randomized without affecting a perception of the image as long as the randomizations follow the correct distribution. The artificial omission of noise when generating images leads to images with a featureless “painterly” look. In particular, when generating human portraits, coarse noise may cause large-scale curling of hair and appearance of larger background features, while the fine noise may bring out the finer curls of hair, finer background detail, and skin pores”[0047], “In an embodiment, the style-based generator system 100 is configured with a direct means to generate stochastic detail by introducing explicit noise inputs. In an embodiment, the noise inputs are single-channel images consisting of uncorrelated Gaussian noise,” The combination of claim 1 is incorporated here.)
Regarding claim 4, Chandran in view of Karras and Hwang teaches:
The computer-implemented method of claim 1, wherein sampling from the distribution comprises generating the additional style code based on an aggregation of two or more style codes selected from the plurality of style codes. (Karras [0043]-[0044], “FIG. 2A illustrates a block diagram of the mapping neural network 110 shown in FIG. 1A, in accordance with an embodiment. A distribution of the training data may be missing a combination of attributes, such as, children wearing glasses. A distribution of the factors of variation in the combination of glasses and age becomes more linear in the intermediate latent space W compared with the latent space custom-character. In an embodiment, the mapping neural network 110 includes a normalization layer 205 and multiple fully-connected layers 210. In an embodiment, eight fully-connected layers 210 are coupled in sequence to produce the intermediate latent code. Parameters (e.g., weights) of the mapping neural network 110 are learned during training and the parameters are used to process the input latent codes when the style-based generator system 100 is deployed to generate the output data. In an embodiment, the mapping neural network 110 generates one or more intermediate latent codes that are used by the synthesis neural network 140 at a later time to generate the output data.” The combination of claim 1 is incorporated here.)
Regarding claim 5, Chandran in view of Karras and Hwang teaches:
The computer-implemented method of claim 4, wherein the aggregation comprises a weighted average. (Karras [0038], “In the case of one dataset of human faces (e.g., FFHQ, Flickr-Faces-HQ), the point represents a sort of an average face (ψ=0).” The combination of claim 1 is incorporated here.)
Regarding claim 6, Chandran in view of Karras and Hwang teaches:
The computer-implemented method of claim 1, wherein sampling from the distribution comprises: sampling from a first distribution to generate a first portion of the additional style code that represents a first subset of the one or more style-based attributes; (Karras See FIG. 2B, first style signal) and sampling from a second distribution to generate a second portion of the additional style code that represents a second subset of the one or more style-based attributes. (Karras See FIG. 2B, first style signal The combination of claim 1 is incorporated here.)
Regarding claim 7, Chandran in view of Karras and Hwang teaches:
The computer-implemented method of claim 1, wherein generating the output 3D shape comprises: inputting the additional style code and an input 3D shape associated with the object into a decoder neural network included in the first trained machine learning model; (Chandran [0004], “A decoder network may then be used to convert the normalized feature map into an output image that combines the style of the style image with the content of the content image.” [0046]) and executing the decoder neural network to generate the output 3D shape. (Chandran [0046], “After training engine 122 has completed training of style transfer model 200, execution engine 124 may execute the trained style transfer model 200 to produce style transfer result 236 from a new content sample 226 and style sample 230. For example, execution engine 124 may input a content image (e.g., an image of a face) and a style image (e.g., an artistic depiction of an object or scene that does not have to be a face) into style transfer model 200 and obtain, as output from style transfer model 200,” [0026])
Regarding claim 9, Chandran in view of Karras and Hwang teaches:
The computer-implemented method of claim 1, wherein sampling from the distribution comprises generating the additional style code based on an aggregation of two or more style codes included in the plurality of style codes. (Karras [0040], “At step 160, the intermediate latent code is converted into a first style signal by the style conversion unit 115.” FIG. 1B and 2A. The combination of claim 1 is incorporated here.)
Regarding claim 10, Chandran in view of Karras and Hwang teaches:
The computer-implemented method of claim 9, wherein the aggregation comprises at least one of an average, a weighted average, or an interpolation.( Karras [0038], “In the case of one dataset of human faces (e.g., FFHQ, Flickr-Faces-HQ), the point represents a sort of an average face (ψ=0).” The combination of claim 1 is incorporated here.)
Regarding claim 11, Chandran in view of Karras and Hwang teaches:
One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to (Claim 12)the rest of claim 11 recites similar limitations of claim 1, thus is rejected accordingly.
claim 12,14, 15, 16 recites similar limitations of claim 2,4, 5, 6 respectively, thus is rejected accordingly.
Regarding claim 17, Chandran in view of Karras and Hwang teaches:
The one or more non-transitory computer-readable media of claim 11, wherein determining the distribution comprises:determining a first distribution associated with a first portion of the plurality of style codes that represents a first level of detail associated with the one or more style-based attributes; (Karras See FIG. 2B, first style signal) and determining a second distribution associated with a second portion of the plurality of style codes that represents a second level of detail associated with the one or more style-based attributes. (Karras See FIG. 2B, first style signal. The combination of claim 1 is incorporated here.)
Regarding claim 18, Chandran in view of Karras and Hwang teaches:
The one or more non-transitory computer-readable media of claim 11, wherein sampling from the distribution comprises generating the additional style code based on an aggregation of two or more style codes included in the plurality of style codes. (Karras [0043]-[0044], “FIG. 2A illustrates a block diagram of the mapping neural network 110 shown in FIG. 1A, in accordance with an embodiment. A distribution of the training data may be missing a combination of attributes, such as, children wearing glasses. A distribution of the factors of variation in the combination of glasses and age becomes more linear in the intermediate latent space W compared with the latent space custom-character. In an embodiment, the mapping neural network 110 includes a normalization layer 205 and multiple fully-connected layers 210. In an embodiment, eight fully-connected layers 210 are coupled in sequence to produce the intermediate latent code. Parameters (e.g., weights) of the mapping neural network 110 are learned during training and the parameters are used to process the input latent codes when the style-based generator system 100 is deployed to generate the output data. In an embodiment, the mapping neural network 110 generates one or more intermediate latent codes that are used by the synthesis neural network 140 at a later time to generate the output data.” The combination of claim 1 is incorporated here.)
Regarding claim 19, Chandran in view of Karras and Hwang teaches:
The one or more non-transitory computer-readable media of claim 11, wherein a style code of the plurality of style codes represents a difference between a first 3D shape and a modified 3D shape, (Karras FIG. 2A, each picture has different shape) and wherein the modified 3D shape is generated by applying at least one of a smoothing augmentation or a coarsening augmentation to the first 3D shape. (Karras [0043]-[0044], “FIG. 2A illustrates a block diagram of the mapping neural network 110 shown in FIG. 1A, in accordance with an embodiment. A distribution of the training data may be missing a combination of attributes, such as, children wearing glasses. A distribution of the factors of variation in the combination of glasses and age becomes more linear in the intermediate latent space W compared with the latent space custom-character. In an embodiment, the mapping neural network 110 includes a normalization layer 205 and multiple fully-connected layers 210. In an embodiment, eight fully-connected layers 210 are coupled in sequence to produce the intermediate latent code. Parameters (e.g., weights) of the mapping neural network 110 are learned during training and the parameters are used to process the input latent codes when the style-based generator system 100 is deployed to generate the output data. In an embodiment, the mapping neural network 110 generates one or more intermediate latent codes that are used by the synthesis neural network 140 at a later time to generate the output data.” The combination of claim 1 is incorporated here.)
claim 20 recites similar limitations of claim 11, thus is rejected accordingly.
Claim(s) 3, 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chandran in view of Karras and Hwang and further in view of Lupascu et al. (US 2023/0267652 A1).
Regarding claim 3, Chandran in view of Karras and Hwang teaches:
The computer-implemented method of claim 1, wherein sampling from the distribution comprises
However, Chandran in view of Karras and Hwang does not, but Lupascu teaches:
generating the additional style code based on a prompt representing at least one style-based attribute.([0060], “As shown in FIG. 2, the artistic content generation system 106 receives style parameters 202. In particular, as illustrated, the artistic content generation system 106 receives the style parameters 202 by receiving a style digital image 204 and a style text prompt 206. As previously mentioned, however, the artistic content generation system 106 receives one of a style digital image or a style text prompt (rather than both) in some embodiments. Further, in some implementations, the artistic content generation system 106 receives multiple style digital images and/or multiple style text prompts as the style parameters 202. Thus, the artistic content generation system 106 receives the style parameters 202 by receiving various combinations of style digital images and style text prompts in some embodiments.”)
Chandran in view of Karras and Hwang teaches generating a style. Lupascu teach generating a style based on a prompt.
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to have combined the teachings of Chandran in view of Karras and Hwang with the specific teachings of Lupascu to enable generating a style based on user’s input.
claim 13 recites similar limitations of claim 3, thus is rejected accordingly.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chandran in view of Karras and Hwang and further in view of Ramani et al. (US 2006/0114252 A1).
Regarding claim 8, Chandran in view of Karras and Hwang teaches:
The computer-implemented method of claim 7,
However, Chandran in view of Karras and Hwang does not, but Ramani teaches:
wherein the output 3D shape comprises at least one of a set of signed distance function values or a set of occupancy values. ([0067], “As noted above, generally a 3D shape S can be represented as a 3D mesh composed of a series of discrete 2D polygons p.sub.i (0.ltoreq.i.ltoreq.n-1) with uniform density. In order to efficiently figure out the contacted polygons of a 3D object along a certain direction, a triple S={p.sub.i|(N.sub.i, A.sub.i, D.sub.i), 0.ltoreq.i.ltoreq.n-1} is used to represent a 3D shape, in which N.sub.i represents the normal of polygon p.sub.i, A.sub.i represents the area of polygon p.sub.i, and D.sub.i represents the signed distance between the mass center C and the polygon p.sub.i. In other embodiments, D.sub.i can be the distance between any predefined origin in 3D space and the polygon p.sub.i.”)
Chandran in view of Karras and Hwang teaches generating 3D shape. Ramani explicitly teach 3D shape is represented as signed distance function.
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to have combined the teachings of Chandran in view of Karras and Hwang with the specific teachings of Ramani to use signed distance to represent 3D shape with reasonable expectation of success.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to YANNA WU whose telephone number is (571)270-0725. The examiner can normally be reached Monday-Thursday 8:00-5:30 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, Alicia Harrington can be reached at 5712722330. 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.
/YANNA WU/Primary Examiner, Art Unit 2615 /YANNA WU/Primary Examiner, Art Unit 2615
Prosecution Insights