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 .
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 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 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Mehr et al (US 20200202045A1) in view of Chandran et al (US 20210279938 A1)
Regarding claim 1, Mehr discloses A computer-implemented method for performing style transfer, the computer- implemented method ([0056] computer-implemented method for designing a 3D modeled object via user-interaction.) comprising:
receiving an input three-dimensional (3D) shape ([0059] system may indeed be any combination of a CAD system, a CAE system, a CAM system, a PDM system and/or a PLM system. In those different systems, modeled objects are defined by corresponding data);
receiving a selection of a style code ([0071] image of the latent space by the function may be the 3D modeled object space or a strict subset of the 3D modeled object space. Decoding a latent vector means applying the decoder to the latent vector.);
generating a 3D model based on the output 3D shape ([0106] autoencoder is applied to the 3D modeled object, thereby outputting a reconstructed 3D modeled object, and the new 3D modeled object is computed by applying the deformation defined by the deformation constraint to the reconstructed 3D modeled object).
Chandran discloses generating, via a trained machine learning model and based on the input 3D shape and the style code, an output 3D shape having at least one first characteristic associated with the input 3D shape and at least one second characteristic associated with the style code ([0027] model trainer is configured to train machine learning models, including a style-based generator machine learning model, which is also referred to herein as the style-based generator, and a super-resolution generator machine learning model, which is also referred to herein as the super-resolution generator)
Mehr and Chandran are combinable because they are from the same field of invention.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify 3D modeled object of Mehr to include generating, via a trained machine learning model and based on the input 3D shape and the style code, an output 3D shape having at least one first characteristic associated with the input 3D shape and at least one second characteristic associated with the style code as described by Chandran.
The motivation for doing so would have been to generating, via a first machine learning model, one or more first appearance maps based on a user selection of one or more styles associated with one or more attributes of a digital face. The method further includes generating, via a second machine learning model, one or more second appearance maps and a first three-dimensional (3D) geometry associated with the digital face based on the one or more first appearance maps and a second 3D geometry associated with the digital face (Chandran, [0008]).
Therefore, it would have been obvious to combine Mehr and Chandran to obtain the invention as specified in claim 1.
Regarding claim 2, Mehr discloses wherein the input 3D shape includes one or more content-based attributes associated with an object ([0076] , a class of 3D modeled objects may designate a set of 3D modeled objects which has a the following property: any first 3D modeled object of the set is similar to, e.g. has a shape similar to, at least a second 3D modeled object of the set.).
Regarding claim 3, Mehr discloses wherein the 3D model comprises a 3D model of the object ([0076] the 3D modeled object space is made of 3D modeled objects of a same class of 3D modeled objects.).
Regarding claim 4, Mehr discloses further comprising generating an input shape representation that includes a plurality of points in proximity to a surface of the input 3D shape ([0099] the 3D modeled object has a given geometrical shape at the providing S10, and the user defines the new geometrical shape by moving the points.).
Regarding claim 5, Mehr discloses wherein generating the output 3D shape via the trained machine learning model comprises executing a set of convolutional layers included in the trained machine learning model to generate multiple sets of features associated with multiple resolutions for each point included in the plurality of points
Chandran discloses wherein generating the output 3D shape via the trained machine learning model comprises executing a set of convolutional layers included in the trained machine learning model to generate multiple sets of features associated with multiple resolutions for each point included in the plurality of points ([0041] the semantics transfer block 302 includes two sets of convolution and AdaIN layers, which include (1) convolution layers 408 and 412 and AdaIN layers 410 and 414 (i.e., a first set of convolution and AdaIN layers), and (2) convolution layers 416 and 420 and AdaIN layers 418 and 422 (i.e., a second set of convolution and AdaIN layers), that are associated with different semantic attributes and process an input image 400 in parallel.)
Mehr and Chandran are combinable because they are from the same field of invention.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify 3D modeled object of Mehr to include wherein generating the output 3D shape via the trained machine learning model comprises executing a set of convolutional layers included in the trained machine learning model to generate multiple sets of features associated with multiple resolutions for each point included in the plurality of points as described by Chandran.
The motivation for doing so would have been to generating, via a first machine learning model, one or more first appearance maps based on a user selection of one or more styles associated with one or more attributes of a digital face. The method further includes generating, via a second machine learning model, one or more second appearance maps and a first three-dimensional (3D) geometry associated with the digital face based on the one or more first appearance maps and a second 3D geometry associated with the digital face (Chandran, [0008]).
Therefore, it would have been obvious to combine Mehr and Chandran to obtain the invention as specified in claim 5.
Regarding claim 6, Mehr discloses wherein the trained machine learning model generates the output 3D shape by generating a plurality of output values for the plurality of points based on a multi-scale feature representation associated with the plurality of points and the style code.
Chandran discloses wherein the trained machine learning model generates the output 3D shape by generating a plurality of output values for the plurality of points based on a multi-scale feature representation associated with the plurality of points and the style code ([0039] the style-based generator 150 repeatedly upscales lower-resolution images using the semantics transfer blocks 302, until a low-resolution appearance map 304 is generated and output by the style-based generator)
Mehr and Chandran are combinable because they are from the same field of invention.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify 3D modeled object of Mehr to include wherein the trained machine learning model generates the output 3D shape by generating a plurality of output values for the plurality of points based on a multi-scale feature representation associated with the plurality of points and the style code as described by Chandran.
The motivation for doing so would have been to generating, via a first machine learning model, one or more first appearance maps based on a user selection of one or more styles associated with one or more attributes of a digital face. The method further includes generating, via a second machine learning model, one or more second appearance maps and a first three-dimensional (3D) geometry associated with the digital face based on the one or more first appearance maps and a second 3D geometry associated with the digital face (Chandran, [0008]).
Therefore, it would have been obvious to combine Mehr and Chandran to obtain the invention as specified in claim 6.
Regarding claim 7, Mehr discloses wherein the style code is based on a difference between a first latent representation of a first 3D shape and a second latent representation of a second 3D shape, and the second 3D shape is generated by applying one or more augmentations to the first 3D shape ([0071] applying the function to vectors of the latent space (hereinafter referred to as “latent vectors”) outputs 3D modeled objects).
Regarding claim 8, Mehr discloses further comprising applying the one or more augmentations to a third 3D shape to generate the input 3D shape ([0071] a probabilistic prior, which may be denoted p(z) in the following, may be given over the latent space z being a notation for a vector of the latent space. In these examples, the prior may be an r priori probability distribution expressing how the latent vectors are distributed over the latent space.).
Regarding claim 9, Mehr discloses wherein the at least one first characteristic comprises at least one content-based attribute of the input 3D shape, and the at least one second characteristic comprises at least one style-based attribute associated with the style code ([0071] image of the latent space by the function may be the 3D modeled object space or a strict subset of the 3D modeled object space.).
Regarding claim 10, Mehr discloses wherein generating the output 3D shape via the trained machine learning model comprises executing the trained machine learning model based on a latent vector corresponding to the style code ([0072] The machine-learnt decoder may be the decoder of an autoencoder. In the context of the method, an autoencoder may be defined as the composition of two feedforward deep neural networks).
Regarding claim 11, Mehr discloses 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 perform ([0166] computer program may comprise instructions executable by a computer, the instructions comprising means for causing the above system to perform the method. The program may be recordable on any data storage medium, including the memory of the system. The program may for example be implemented in digital electronic circuitry, or in computer hardware, firmware, software, or in combinations of them.) the steps of:
receiving an input three-dimensional (3D) shape ([0059] system may indeed be any combination of a CAD system, a CAE system, a CAM system, a PDM system and/or a PLM system. In those different systems, modeled objects are defined by corresponding data);;
receiving a selection of a style code ([0071] image of the latent space by the function may be the 3D modeled object space or a strict subset of the 3D modeled object space. Decoding a latent vector means applying the decoder to the latent vector.);;
generating, via a trained machine learning model and based on the input 3D shape and the style code, an output 3D shape having at least one first characteristic associated with the input 3D shape and at least one second characteristic associated with the style code; and
generating a 3D model based on the output 3D shape ([0106] autoencoder is applied to the 3D modeled object, thereby outputting a reconstructed 3D modeled object, and the new 3D modeled object is computed by applying the deformation defined by the deformation constraint to the reconstructed 3D modeled object).
Chandran discloses generating, via a trained machine learning model and based on the input 3D shape and the style code, an output 3D shape having at least one first characteristic associated with the input 3D shape and at least one second characteristic associated with the style code ([0027] model trainer is configured to train machine learning models, including a style-based generator machine learning model, which is also referred to herein as the style-based generator, and a super-resolution generator machine learning model, which is also referred to herein as the super-resolution generator)
Mehr and Chandran are combinable because they are from the same field of invention.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify 3D modeled object of Mehr to include generating, via a trained machine learning model and based on the input 3D shape and the style code, an output 3D shape having at least one first characteristic associated with the input 3D shape and at least one second characteristic associated with the style code as described by Chandran.
The motivation for doing so would have been to generating, via a first machine learning model, one or more first appearance maps based on a user selection of one or more styles associated with one or more attributes of a digital face. The method further includes generating, via a second machine learning model, one or more second appearance maps and a first three-dimensional (3D) geometry associated with the digital face based on the one or more first appearance maps and a second 3D geometry associated with the digital face (Chandran, [0008]).
Therefore, it would have been obvious to combine Mehr and Chandran to obtain the invention as specified in claim 11.
Regarding claim 12, Mehr discloses wherein the style code is based on a difference between a first latent representation of a first 3D shape and a second latent representation of a second 3D shape, and the second 3D shape is generated by applying one or more augmentations to the first 3D shape ([0071] applying the function to vectors of the latent space (hereinafter referred to as “latent vectors”) outputs 3D modeled objects).
Regarding claim 13, Mehr discloses wherein the one or more augmentations comprise at least one of a smoothing augmentation or a coarsening augmentation ([0142] other term is a smoothness term that is a distance between the explored latent vector z and the result z.sub.0 of applying the encoder to the 3D modeled object).
Regarding claim 14, Mehr discloses wherein determining the style code comprises:
converting the difference between the first latent representation and the second latent representation into a plurality of intermediate representations ([0128] Rewarding may generally mean that the minimizing of the energy is conceived to tend to a result (i.e. the optimal latent vector) which is close to the projection of the 3D modeled object onto the latent space); and
performing one or more pooling operations on the plurality of intermediate representations ([0128] the exploring of the latent vectors may be performed iteratively (that is, latent vectors are explored one by one, until the optimal latent vector is found) and may start from a first latent vector which is the projection of the 3D modeled object onto the latent space.)
Regarding claim 15, Mehr discloses wherein the instructions further cause the one or more processors to perform the step of generating an input shape representation that includes a plurality of points in proximity to a surface of the input 3D shape ([0099] the 3D modeled object has a given geometrical shape at the providing S10, and the user defines the new geometrical shape by moving the points.).
Regarding claim 16, Mehr discloses wherein the input shape representation further comprises a plurality of signed distance function values associated with a grid of points disposed around the input 3D shape ([0132] the distance is an efficient way to measure and reward closeness between latent vectors and the encoded 3D modeled object.).
Regarding claim 17, Mehr discloses wherein the input 3D shape includes one or more content-based attributes associated with an object ([0076] , a class of 3D modeled objects may designate a set of 3D modeled objects which has a the following property: any first 3D modeled object of the set is similar to, e.g. has a shape similar to, at least a second 3D modeled object of the set.)..
Regarding claim 18, Mehr discloses wherein the 3D model comprises a 3D model of the object ([0076] the 3D modeled object space is made of 3D modeled objects of a same class of 3D modeled objects.).
Regarding claim 19, Mehr discloses wherein the at least one first characteristic comprises at least one content-based attribute of the input 3D shape, and the at least one second characteristic comprises at least one style- based attribute associated with the style code ([0071] image of the latent space by the function may be the 3D modeled object space or a strict subset of the 3D modeled object space.).
Regarding claim 20, Mehr discloses A system ([0059] system may indeed be any combination of a CAD system, a CAE system, a CAM system, a PDM system and/or a PLM system. In those different systems, modeled objects are defined by corresponding data), comprising:
one or more memories that store instructions ([0166] recordable on any data storage medium), and
one or more processors that are coupled to the one or more memories ([0166] computer program may comprise instructions executable by a computer, the instructions comprising means for causing the above system to perform the method. The program may be recordable on any data storage medium, including the memory of the system. The program may for example be implemented in digital electronic circuitry, or in computer hardware, firmware, software, or in combinations of them.) and,
when executing the instructions, are configured to perform the steps of:
A computer-implemented method for performing style transfer, the computer- implemented method ([0056] computer-implemented method for designing a 3D modeled object via user-interaction.) comprising:
receiving an input three-dimensional (3D) shape;
receiving a selection of a style code ([0071] image of the latent space by the function may be the 3D modeled object space or a strict subset of the 3D modeled object space. Decoding a latent vector means applying the decoder to the latent vector.);
generating a 3D model based on the output 3D shape ([0106] autoencoder is applied to the 3D modeled object, thereby outputting a reconstructed 3D modeled object, and the new 3D modeled object is computed by applying the deformation defined by the deformation constraint to the reconstructed 3D modeled object).
Chandran discloses generating, via a trained machine learning model and based on the input 3D shape and the style code, an output 3D shape having at least one first characteristic associated with the input 3D shape and at least one second characteristic associated with the style code ([0027] model trainer is configured to train machine learning models, including a style-based generator machine learning model, which is also referred to herein as the style-based generator, and a super-resolution generator machine learning model, which is also referred to herein as the super-resolution generator)
Mehr and Chandran are combinable because they are from the same field of invention.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify 3D modeled object of Mehr to include generating, via a trained machine learning model and based on the input 3D shape and the style code, an output 3D shape having at least one first characteristic associated with the input 3D shape and at least one second characteristic associated with the style code as described by Chandran.
The motivation for doing so would have been to generating, via a first machine learning model, one or more first appearance maps based on a user selection of one or more styles associated with one or more attributes of a digital face. The method further includes generating, via a second machine learning model, one or more second appearance maps and a first three-dimensional (3D) geometry associated with the digital face based on the one or more first appearance maps and a second 3D geometry associated with the digital face (Chandran, [0008]).
Therefore, it would have been obvious to combine Mehr and Chandran to obtain the invention as specified in claim 20.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHIVANG I PATEL whose telephone number is (571)272-8964. The examiner can normally be reached on M-F 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, Alicia Harrington can be reached on (571) 272-2330. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SHIVANG I PATEL/Primary Examiner, Art Unit 2615
Prosecution Insights