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 § 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.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 1-20 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 1, 12 and 20 recites the limitation "using a first image of a first object… wherein a number of first objects is at least two, a number of first images is at least two," in lines 2 and 4, lines 5-7, and lines 2-4 (respectively). There is insufficient antecedent basis for this limitation in the claims. This is because of introducing a singular first image and a singular first object and then referring to those singular instances as plural. It is not clear how “a first image” can be “two” and how “a first object” can be “two”. Examiner is interpreting this as multiple images considered a first image with each of those images having a same object.
Claim 2 recites the limitation "wherein the inputting a single second image of a second object and a second label corresponding to the second image into the first algorithm model trained such that the first algorithm model generates a second avatar of the second object according to the first avatar comprises:" in the first three lines. There is insufficient antecedent basis for this limitation in the claim. This is because it is unclear whether these are new instances or old instances (first introduced in parent claim(s)) of “second image”, “second object”, “second label”, and “second avatar”.
Claim 3 recites the limitation "a third avatar" in line 1. There is insufficient antecedent basis for this limitation in the claim. This is because it is unclear whether this is a new instance or old instance (first introduced in parent claim(s)) of “third avatar”.
Claim 3 recites the limitation "the first avatars" in line 1, “each of first avatars” in line 6 and claim 14 recites the limitation "each of first avatars" in line 5. There is insufficient antecedent basis for this limitation in the claim. This is because it is unclear which first avatars (in plural) are being referred to since the parent claim recites a singular “first avatar”.
Claim 4 and 15 recites the limitation "texture information of an avatar" in each respective last line. There is insufficient antecedent basis for this limitation in the claim. This is because it is unclear whether this is a new instance or old instance (first introduced in parent claim(s)) of “avatar”.
Claims 5 and 16 recites the limitation "a sixth image…the sixth image" in lines 4-6 of each claim. There is insufficient antecedent basis for this limitation in the claim. This is because it is unclear how the sixth image exists without a mention of a third, fourth and fifth image.
Claim 5 recites the limitation "wherein the training a first algorithm model using a first image of a first object and a first label corresponding to the first image comprises:" in the first two lines. There is insufficient antecedent basis for this limitation in the claim. This is because it is unclear whether these are new instances or old instances (first introduced in parent claim(s)) of “first algorithm model”, “first image”, “first label”, and “first object”.
Claims 7 and 18 recites the limitation "obtain the three-dimensional texture information of the first avatar" in the last two lines. There is insufficient antecedent basis for this limitation in the claim. It is unclear what “the three-dimensional texture information” is referring to since previously “texture information” is for “the first object” (see parent claims 6 and 17, second to last and third to last lines), whereas here it refers to the previous “texture information” being of “the first avatar”.
Claim 9 recites the limitation "wherein the determining shadow information of the first object according to the sampling point in the first image, the object mesh of the first object in the first image, and the object pose of the first object in the first image comprises:.. the shadow information of the first avatar " in the first three lines and last line. There is insufficient antecedent basis for this limitation in the claim. This is because it is unclear whether these are new instances or old instances (first introduced in parent claim(s)) of “shadow information”.
Claim 10 recites the limitation "wherein the determining a shadow value of the sampling point under the object pose on the basis of the object shadow domain and according to the sampling point in the first image, the object mesh of the first object in the first image and the object pose of the first object in the first image comprises:" in first four lines. There is insufficient antecedent basis for this limitation in the claim. This is because it is unclear whether this is a new instance or old instance (first introduced in parent claim(s)) of “shadow value”.
Claim 11 and 19 recites the limitations "the object mesh" in line 2 and line 3 (respectively), “performing interpolation calculation… subjected to interpolation calculation… is an interpolation calculation result” in lines 4-6 and lines 5-7 (respectively), and “the avatars of the at least two objects” in lines 6-7 and lines 7-8. There is insufficient antecedent basis for this limitation in the claim. This is because it is unclear what “object mesh” is referring to (due to no mention or introduction of such previously or in parent claim), it is unclear whether this is a new instance or old instance of “interpolation calculation” each time it is repeated, and it is unclear which avatars (or if all) are being referred to by “the avatars” since many avatars (including a fourth but without a third) are aforementioned.
Claims 2-11 and 13-19 rejected under 35 U.S.C. 112(b) since they depend on a claim that is rejected under 35 U.S.C. 112(b).
Note. Most likely these claims depend on some dependent claim or are missing elements.
In order to fix this issue, dependency should be reviewed and any first instance of an element
should be made clear that it’s a first instance and should be referred to as “a” or “an” instead of
“the”, and if multiple instances exist, further instances should be further distinguished for example by saying “first”, “second”, and/or “third” etc.
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.
Claim(s) 1, 12 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Joachim (U.S. Patent Application Publication No. 2024/0378832), hereinafter referenced as Joachim, in view of Corona et al. (LISA: Learning Implicit Shape and Appearance of Hands), hereinafter referenced as Corona.
Regarding claim 1, Joachim teaches a method for generating a virtual avatar, comprising: (abstract teaches "methods...utilize three-dimensional representations of two-dimensional" and paragraph 707 teaches "system 106 generates the three-dimensional body model 6122"); to utilize 3D representations (virtual avatars) they are first generated; training a first algorithm model using a first image of a first object and a first label corresponding to the first image (paragraph 712 teaches "the scene-based image editing system 106 trains the three-dimensional hand neural network 6114b to extract three-dimensional pose/shape data from hands of two-dimensional images based on a training dataset including hands and corresponding three-dimensional hand models" and paragraph 578 teaches "automatically label pixels of the two-dimensional image 4500 into object classifications based on detected objects in the two-dimensional image"); the neural network here is a first algorithm model and uses two-dimensional/first image of first object/hand as well as first label since the pixels of 2D image are labeled based on detected objects; such that the first algorithm model generates a first avatar of the first object, (paragraph 546 teaches "neural networks for generating one or more three-dimensional meshes" and paragraph 574 teaches "TEXTURE represents a texture applied to the three-dimensional meshes"); this shows first algorithm model (aforementioned neural network) generating first avatar(the 3D textured mesh) of first object [note: avatar definition here is consistent with applicant's disclosure paragraph 41 which mentions "avatar: a textured drivable three-dimensional model"]; wherein a number of first objects is at least two, a number of first images is at least two, and one first avatar is an avatar of one first object (paragraph 712 teaches "extract three-dimensional pose/shape data from hands of two-dimensional images based on a training dataset including hands"); this shows first object and images being at least two (since plural mention of images which would each have a hand) and the 3D pose/data shows one first avatar of one first object/hand; and inputting a single second image of a second object and a second label corresponding to the second image into the first algorithm model trained (paragraph 698 teaches "labels body parts that correspond to one or more of the bones...the scene-based image editing system 106 also generates separate bounding boxes corresponding to the hands (e.g., a first bounding box for a first hand and a second bounding box for a second hand)."); label of body part such as second hand would be considered second label (corresponding to second image since in it), second hand here would be second object and as shown in fig. 61B, the bounding box 6110a of such (form single second image) is input to the aforementioned neural network model (which is trained with the first hand data); such that the first algorithm model generates a second avatar of the second object according to the first avatar, (fig. 61B shows 3D hand model 6124 generated from hand neural network 6114b and is based on the bounding boxes 6110a); this (which is second avatar of second object when viewed in combination with previous citation of second hand") would be according to first avatar since uses same network/model and is based on the bounding box of such; wherein a number of the second object is one, the second avatar is an avatar of the second object, (paragraph 698 teaches "a second bounding box for a second hand"); this shows second hand as singular thus the number of second object is one and as aforementioned above, the second avatar is of the second object; the second object is a homogeneous object which is different from the first object, (paragraph 866 teaches "uniform/better formed triangulation in a three-dimensional mesh"); uniform shows object would be homogeneous and also second hand is different from first since they are two different hands.
However, Joachim fails to explicitly teach and the first avatar and the second avatar are implicit avatars.
However, Corona teaches and the first avatar and the second avatar are implicit avatars (Corona, page 1, fig. 1 description teaches "LISA hand model is defined by an articulated implicit representation learned from multi-view RGB videos annotated with
coarse 3D hand poses (left)"); this shows the hand/object avatars from above would be implicit avatars. Corona is considered to be analogous art because it is reasonably pertinent to the problem faced by the inventor of generating virtual avatars using and as implicit representations. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Joachim's invention with the implicit representation techniques of Corona to greatly improve geometry (page 4, right column, third paragraph). This leads to more accurate output.
Regarding claim 12, the apparatus claim 12 recites similar limitations as method claim 1, and thus is rejected under similar rationale. In addition, Joachim, fig. 94 teaches device/apparatus 9400 with memory 9404, processor 9402, storage 9406, and claim 18 teaches “non-transitory computer readable medium storing executable instructions which, when executed by a processing device,”.
Regarding claim 20, the non-transitory computer-readable storage medium claim 20 recites similar limitations as method claim 1, and thus is rejected under similar rationale. In addition, Joachim, claim 18 teaches “non-transitory computer readable medium storing executable instructions which, when executed by a processing device,”.
Claim(s) 2-5 and 13-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Joachim and Corona as applied to claim 1 and 12 above, and further in view of Aliakbarian et al. (HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observations), hereinafter referenced as Ali.
Regarding claim 2, the combination of Joachim and Corona teaches wherein the inputting a single second image of a second object and a second label corresponding to the second image into the first algorithm model trained such that the first algorithm model generates a second avatar of the second object according to the first avatar comprises: generating a third avatar according to the first avatar (Joachum, paragraph 714 teaches “a merging model 6126 to merge the three-dimensional body model 6122 with the three-dimensional hand model 6124 (e.g., as generated in FIG. 61B). For example, the scene-based image editing system 106 utilizes the merging model 6126 to generate a three-dimensional human model 6128 by joining the three-dimensional hand model 6124 with the three-dimensional body model 6122”); the body model 6122 from combining previous models shows third avatar generated and is based on/according to first avatar since uses such from hand models 6124; generating one or more third images with a different viewing angle from the second image according to the third avatar (paragraph 714 teaches “within three-dimensional space according to a camera space”); this indicates a third image since is of the aforementioned third avatar (within a 3D space) thus would require third depiction/image and since it’s a camera space one of ordinary skill in the art would understand that this camera space would be a different viewing angle from the second image (since “a” camera space refers to a new one rather than “the” camera space); wherein the fourth image is an image of the second object having a same viewing angle as the second image and generated by using an adjusted third avatar, (Corona, fig. 1 teaches a fourth image of a hand in fourth row); this (hand and considered second object in fourth frame) comes after third avatar/model of hand thus is generated by using adjustments of such and it is shown to have the same viewing angle as the second frame; and the fifth image is an image of the second object having a same viewing angle as the third image and generated by using the adjusted third avatar (Corona, fig. 1 teaches a fifth image of a hand in fifth row); this (hand and considered second object in fifth frame) comes after third avatar/model of hand thus is generated by using adjustments of such and it is shown to have the same viewing angle as the third frame; and taking the adjusted third avatar as the second avatar (Joachim, fig. 37 “object of interest” shows taking an adjusted/segmented third avatar as the second avatar in the middle picture).
However, the combination of Joachim and Corona fails to teach and adjusting the third avatar to reduce a residual error between the second image and a fourth image and a residual error between the third image and a fifth image,
However, Ali teaches and adjusting the third avatar to reduce a residual error between the second image and a fourth image and a residual error between the third image and a fifth image, (Ali, page 5, right column, first paragraph teaches “adjusts the pose parameters to minimize an energy function… define the data energy term, we define the residual R… the difference between the predicted head/hand joint to that of the observation.”); this shows to minimize residual energy for avatars which is connected with error minimization, therefore, one of ordinary skill in the art would understand that the displacement mentioned in paragraph 848 of Joachim would also be done for adjusting of third pose/avatar and that the minimization/reducing of the residual error would be between any two frames such as second image and fourth image as well as third image and fifth image. Ali is considered to be analogous art because it is reasonably pertinent to the problem faced by the inventor of residual errors and minimizations thereof in avatars and hand models. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Joachim and Corona with the residual error techniques of Ali to ensure further optimized to improve accuracy (Ali, page 8, left col. Last paragraph). This leads to a more efficient invention overall.
Regarding claim 3, the combination of Joachim, Corona and Ali teaches wherein the generating a third avatar according to the first avatars comprises: determining a parameter of an object code (Joachim, paragraph 178 teaches “an encoder neural network extracts latent code from a noise vector or from a digital image. A generator neural network (or a combination of generator neural networks) generates a modified digital image by combining extracted latent code” and paragraph 345 teaches “a feature vector includes a set of values corresponding to latent and/or patent attributes related to a digital image”); latent code shows object code here and feature vector for latent attributes shows determining parameter of such; and a color correction parameter of each of the first objects, (Corona, page 4, third paragraph teaches “which maps the pose parameter θ, shape parameter β+ and the color parameter γ to an implicit representation”); this shows color parameter alongside the shapes and poses meaning the first objects would also have such, also this is for color correction since previous paragraph mentions “formulate the learning”; wherein one object code is used to represent one object, (Corona, page 5, second paragraph teaches “we assign the same latent code for all images of the same person”); same latent/object code given to same person means one latent/object code is used to represent one object/person; and an avatar of the object represented by the object code is able to be obtained through the object code (Corona, page 5, first paragraph teaches “latent codes to control the generation process”); this shows avatar of object represented by object code would be generated/obtained (thus is able to) by using the latent/object code; and synthesizing the third avatar with each of first avatars according to the parameter of the object code of the first objects (Corona, fig. 1 shows third avatar in third column after a first avatar in first column and fig. 2 shows parameters used in calculations such as latent vectors shown in the middle); this shows third avatar is synthesized with each first avatar and would be according to parameter of object code (latent vector) of the first avatar and object thereof; and synthesizing a color of the third avatar with a color of the first avatar according to the color correction parameter (Corona, fig. 1 shows third avatar in third column with color of first avatar in first column); this would be according to color correction parameter since the pose and color are mapped to the implicit representations as aforementioned. The same motivations used in claim 1 apply here in claim 3.
Regarding claim 4, the combination of Joachim, Corona and Ali teaches wherein the adjusting the third avatar comprises: adjusting a multilayer perceptron in the first algorithm model, (Joachim, paragraph 191 teaches “an MLP-based mapping network produces a random style code w from a normalized random Gaussian noise z”); using gaussian noise shows adjusting the MLP; wherein the multilayer perceptron in the first algorithm model is used for generating three-dimensional texture information of an avatar (Joachim, paragraph 355 teaches “match the feature map spatial dimension as a 2-layer multilayer perceptron (MLP). Indeed, in one or more embodiments, the scene-based image editing system 106 utilizes f.sub.gate as a filter that selects attribute features that are relevant to the object of interest”); attribute features include 3D texture information (since texture generated from such) of aforementioned avatar.
Regarding claim 5, the combination of Joachim and Corona teaches wherein the training a first algorithm model using a first image of a first object and a first label corresponding to the first image comprises: generating the first avatar of the first object using the first image and the first label corresponding to the first image (Joachim, paragraph 712 teaches "the scene-based image editing system 106 trains the three-dimensional hand neural network 6114b to extract three-dimensional pose/shape data from hands of two-dimensional images based on a training dataset including hands and corresponding three-dimensional hand models" and paragraph 578 teaches "automatically label pixels of the two-dimensional image 4500 into object classifications based on detected objects in the two-dimensional image"); the neural network here is a first algorithm model and uses two-dimensional/first image of first object/hand as well as first label since the pixels of 2D image are labeled based on detected objects, thus the first avatar is generated (of the first object) using such; generating a sixth image of the first object according to the first avatar (Corona, fig. 1 sixth column shows sixth image of first object/hand generated); this is according to first avatar since comes after such and is based on such;
However, the combination of Joachim and Corona fails to teach and adjusting the first avatar to reduce a residual error between the sixth image regenerated on the basis of an adjusted first avatar and the first image
However, Ali teaches and adjusting the first avatar to reduce a residual error between the sixth image regenerated on the basis of an adjusted first avatar and the first image (Ali, page 5, right column, first paragraph teaches “adjusts the pose parameters to minimize an energy function… define the data energy term, we define the residual R… the difference between the predicted head/hand joint to that of the observation.”); this shows to minimize residual energy for avatars which is connected with error minimization, therefore, one of ordinary skill in the art would understand that the displacement mentioned in paragraph 848 of Joachim would also be done for adjusting of first pose/avatar and that the minimization/reducing of the residual error would be between any two frames such as seventh image in fig. 1 of Corona (which is regenerated sixth image on basis of adjusted first avatar) and first image. The same motivations used in claim 2 apply here in claim 5.
Regarding claim 13, the apparatus claim 13 recites similar limitations as method claim 2, and thus is rejected under similar rationale.
Regarding claim 14, the apparatus claim 14 recites similar limitations as method claim 3, and thus is rejected under similar rationale.
Regarding claim 15, the apparatus claim 15 recites similar limitations as method claim 4, and thus is rejected under similar rationale.
Regarding claim 16, the apparatus claim 16 recites similar limitations as method claim 5, and thus is rejected under similar rationale.
Claim(s) 11 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Joachim and Corona as applied to claims 1 and 12 above, and further in view of Chen et al. (Hand Avatar: Free-Pose Hand Animation and Rendering from Monocular Video), hereinafter referenced as Chen.
Regarding claim 11, the combination of Joachim and Corona teaches
further comprising one or more selected from the following: adjusting a geometry of the second avatar in response to changing the object mesh and/or a geometry parameter of the second avatar (Joachim, paragraph 848 teaches “utilizes a plurality of neural networks to generate the displacement three-dimensional mesh 7902 including a plurality of vertices and faces that form a geometry representing objects from the two-dimensional image”); the displacement is geometry of second avatar adjusting and it’s in response to changing the vertices and faces that form geometry (thus the geometry parameter) of a model such as second avatar; and the first object and the second object each being hands of different persons (Joachim, paragraph 131 teaches “a person's face, hair, or leg can be objects that are part of another object (e.g., the person's body)”); part of another object here means each of the hands would be part of another/different person.
However, the combination of Joachim and Corona fails to teach acquiring object codes of at least two objects, performing interpolation calculation using the at least two object codes, and generating a fourth avatar using the object codes subjected to interpolation calculation, wherein an appearance of the fourth avatar is an interpolation calculation result of the avatars of the at least two objects;
However, Chen teaches acquiring object codes of at least two objects, (Chen, page 3, paragraph 2 teaches “attached latent codes to mesh vertices, which can diffuse into space with sparse convolution”); latent codes here show object codes acquired and since of mesh vertices they’d be for the aforementioned two objects; performing interpolation calculation using the at least two object codes, (Chen, page 5, Albedo Field paragraph in the left column teaches “For a query q, we find Nn nearest points in ˜P and interpolate A using inverse Euclidean distances as the weights. Thereby, we obtain the albedo encoding Aq ∈ R^D^a and then fed it to an MLP”); this shows interpolation which uses the latent/object codes; and generating a fourth avatar using the object codes subjected to interpolation calculation, (Chen, fig. 4 shows fourth avatar in “volume rendering” which is based on/using the aforementioned interpolation and latent/object codes); wherein an appearance of the fourth avatar is an interpolation calculation result of the avatars of the at least two objects; (Chen, fig. 4 flowchart shows “point interpolation” used to arrive at fourth avatar); this means appearance of fourth avatar is interpolation calculation result of the avatars of previous two objects. Chen is considered to be analogous art because it is reasonably pertinent to the problem faced by the inventor of hand interpolation and animation. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Joachim and Corona with the interpolation techniques of Chen to ensure high-resolution topology structure to improve the shape-fitting capacity of hand mesh (Chen, page 8, conclusion). This means more realistic output.
Regarding claim 19, the apparatus claim 19 recites similar limitations as method claim 1, and thus is rejected under similar rationale.
Allowable Subject Matter
Claims 6-10 and 17-18 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.
The following is a statement of reasons for the indication of allowable subject matter:
Regarding claim 6, the closest prior art of (or combination of) the combination of Joachim and Corona teaches wherein the generating the first avatar of the first object using the first image and the first label corresponding to the first image comprises: determining a geometry of the first object according to a sampling point in the first image, and an object pose and an object mesh of the first object in the first image (Joachim, paragraph 868 teaches “scene-based image editing system 106 determines that two or three iterations provide a plurality of sampled points that result in a three-dimensional mesh that preserves the boundaries of the objects of the two-dimensional image while remaining consistent with the density map”); this shows boundary/geometry of first object determined according to sampling point, mesh and a aforementioned pose;
determining shadow information of the first object according to the sampling point in the first image, the object mesh of the first object in the first image, and the object pose of the first object in the first image (Joachim, paragraph 574 teaches “(SHADOW_FACTOR(x))*TEXTURE(x)…SHADOW_FACTOR is a value that the scene-based image editing system 106 generates by sampling the appropriate shadow map, with a larger sampling radius producing softer shadows….TEXTURE represents a texture applied to the three-dimensional meshes”); this shows shadow information (of first object in first image) determined according to sampling point and mesh (since uses texture associated with mesh), also would be according to pose since the pose would also be in the first image;
determining three-dimensional texture information of the first object according to an object code of the first object in the first image, the sampling point and the object mesh of the first object in the first image;
and obtaining the first avatar of the first object according to the geometry of the first object, the three-dimensional texture information of the first object and a shadow value of the first avatar, wherein the first label comprises: the object pose and the object mesh of the first object in the first image. However, the combination of Joachim and Corona fails to teach determining three-dimensional texture information of the first object according to an object code of the first object in the first image, the sampling point and the object mesh of the first object in the first image;
and obtaining the first avatar of the first object according to the geometry of the first object, the three-dimensional texture information of the first object and a shadow value of the first avatar, wherein the first label comprises: the object pose and the object mesh of the first object in the first image.
Furthermore, no prior art of record either alone or in combination teaches
determining three-dimensional texture information of the first object according to an object code of the first object in the first image, the sampling point and the object mesh of the first object in the first image;
and obtaining the first avatar of the first object according to the geometry of the first object, the three-dimensional texture information of the first object and a shadow value of the first avatar, wherein the first label comprises: the object pose and the object mesh of the first object in the first image when read in light of the rest of the limitations in claim 6 and the claims to which claim 6 depends and thus claim 6 contains allowable subject matter.
Regarding claim 17, the prior art of record either alone or in combination fails to teach
determine three-dimensional texture information of the first object according to an object code of the first object in the first image, the sampling point and the object mesh of the first object in the first image; and obtain the first avatar of the first object according to the geometry of the first object, the three-dimensional texture information of the first object and a shadow value of the first avatar, wherein the first label comprises: the object pose and the object mesh of the first object in the first image when read in light of the rest of the limitations in claim 17 and the claims to which claim 17 depends and thus claim 17 contains allowable subject matter. The same reasoning for the indication of allowable subject matter in claim 6 applies here to claim 17.
Claims 7-10 and 18 contain allowable subject matter because they depend on a claim that contains allowable subject matter.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Liu et al. (U.S. Patent Application Publication No. 2023/0401815) paragraph 34 teaches “neural network model may be trained (208) using a loss function that minimizes a residual between synthesized images and ground truth (“g.t.”) images”; this shows reducing residual error in images using neural network.
Bernardini (U.S. Patent Application Publication No. 2023/0143670) paragraph 44 teaches “for the training of a neural network for image recognition comprising: loading a mathematical model of the object 2, computing physically stable poses of the object 2 using its geometry… uniform coloured… extracting the labels of the object”; this shows acquire images and labels for object, has math/implicit models and 3d model as well as uniform/homogeneous property such as color.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NAUMAN U AHMAD whose telephone number is (703)756-5306. The examiner can normally be reached Monday - Friday 9:00am - 5:00pm.
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, Kee Tung can be reached at (571) 272-7794. 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.
/N.U.A./Examiner, Art Unit 2611
/KEE M TUNG/Supervisory Patent Examiner, Art Unit 2611
Prosecution Insights