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 § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 11-16, 32, 35, 37, 39, 42, 43 and 46 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by US 2023/0388470 to Aluru et al. (“Aluru”).
Regarding claim 11, Aluru discloses a method, comprising:
at a device:
implicitly learning a parametric distribution of data by at least one neural network (Fig. 4; paragraphs 29, 38-42, 66-67, wherein the trained neural network implicitly learns the generated 3D image content, such as a point cloud (fig. 4) and corresponding to a parametric distribution of data, using 2D images from different viewpoints); and
outputting the parametric distribution of the data (Fig. 4; paragraphs 29, 66-67, wherein the 3D point cloud output corresponds to outputting the parametric distribution of data implicitly learned by the neural network from different viewpoints).
Regarding claim 12, Aluru discloses the method of claim 11, wherein the data is unstructured (Fig. 4; paragraphs 29, 38-42, 66-67, wherein 3D point cloud data is “unstructured” as seen in figure 4).
Regarding claim 13, Aluru discloses the method of claim 11, wherein the data is unordered (Fig. 4; paragraphs 29, 38-42, 66-67, wherein 3D point cloud data is “unordered” as seen in figure 4).
Regarding claim 14, Aluru discloses the method of claim 11, wherein the data has non-uniform sparsity (Fig. 4; paragraphs 29, 38-42, 66-67, wherein 3D point cloud data has “non-uniform sparsity” as seen in figure 4).
Regarding claim 15, Aluru discloses the method of claim 11, wherein the data is low-dimensional data (Fig. 4; paragraphs 29, 38-42, 66-67, wherein 3D point cloud data is “low-dimensional data” as seen in figure 4).
Regarding claim 16, Aluru discloses the method of claim 11, wherein the data is a three-dimensional (3D) point cloud (Fig. 4; paragraphs 29, 38-42, 66-67, wherein the data is 3D point cloud data).
Regarding claim 32, Aluru discloses the method of claim 11, wherein the parametric distribution of the data is a blob (Fig. 4; paragraphs 29, 38-42, 66-67, wherein 3D point cloud data corresponds to the broadest reasonable interpretation of a “blob” of data (i.e. vague shape), as seen in figure 4).
Regarding claim 35, Aluru discloses the method of claim 11, wherein the parametric distribution of the data is output to a downstream task (paragraph 43, wherein the point cloud generated is output for a user viewing corresponding to a downstream task).
Regarding claim 37, Aluru disclose the method of claim 11, wherein the parametric distribution of the data is a learned positional embedding, and wherein the learned positional embedding is output for generating a coordinate-based neural representation (Fig. 4; paragraphs 29, 38-42, 66-67, wherein the generated 3D image content, such as a point cloud (fig. 4) and corresponding to learned positional embedding based on 2D images from different viewpoints. The point cloud is output corresponds to “a coordinate-based neural representation”).
Regarding claim 39, Aluru discloses a system, comprising:
a non-transitory memory storage comprising instructions (paragraphs 130-133); and
one or more processors in communication with the memory, wherein the one or more processors execute the instructions to (paragraphs 130-133):
implicitly learn a parametric distribution of data by at least one neural network (Fig. 4; paragraphs 29, 38-42, 66-67, wherein the trained neural network implicitly learns the generated 3D image content, such as a point cloud (fig. 4) and corresponding to a parametric distribution of data, using 2D images from different viewpoints); and
output the parametric distribution of the data (Fig. 4; paragraphs 29, 66-67, wherein the 3D point cloud output corresponds to outputting the parametric distribution of data implicitly learned by the neural network from different viewpoints).
Regarding claim 42, Aluru discloses the system of claim 39, wherein the parametric distribution of the data is a blob (Fig. 4; paragraphs 29, 38-42, 66-67, wherein 3D point cloud data corresponds to the broadest reasonable interpretation of a “blob” of data (i.e. vague shape), as seen in figure 4).
Regarding claim 43, Aluru discloses a non-transitory computer-readable media storing computer instructions which when executed by one or more processors of a device cause the device to (paragraphs 130-133):
implicitly learn a parametric distribution of the data by at least one neural network (Fig. 4; paragraphs 29, 38-42, 66-67, wherein the trained neural network implicitly learns the generated 3D image content, such as a point cloud (fig. 4) and corresponding to a parametric distribution of data, using 2D images from different viewpoints); and
output the parametric distribution of the data (Fig. 4; paragraphs 29, 66-67, wherein the 3D point cloud output corresponds to outputting the parametric distribution of data implicitly learned by the neural network from different viewpoints).
Regarding claim 46, Aluru discloses the non-transitory computer-readable media of claim 43, wherein the parametric distribution of the data is a blob (Fig. 4; paragraphs 29, 38-42, 66-67, wherein 3D point cloud data corresponds to the broadest reasonable interpretation of a “blob” of data (i.e. vague shape), as seen in figure 4).
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 17 and 36 are rejected under 35 U.S.C. 103 as being unpatentable over US 2023/0388470 to Aluru et al. (“Aluru”) in view of US 2023/0343026 to Wang et al. (“Wang”).
Regarding claim 17, Aluru discloses the method of claim 11, that include train a neural network to reconstruct a 3D point cloud from 2D images (paragraph 38).
Aluru does not disclose expressly wherein the at least one neural network includes at least one kernel.
Wang discloses a process of reconstructing a 3D point cloud from 2D images using a trained convolutional neural network (CNN), wherein, as is known in the art, a CNN comprises at least one kernel/filter/matrix in the convolution process (Figs. 1, 2; paragraphs 36-45).
Aluru & Wang are combinable because they are from the same art of processing 2D images to reconstruct a 3D point cloud.
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to incorporate the technique of using a CNN, including at least one kernel, to generate a 3D point cloud, as taught by Wang, into the process for generating a 3D point cloud disclosed by Aluru.
The suggestion/motivation for doing so would have been to provide construction of an accurate and clear 3D point cloud (Wang, paragraphs 07, 33, 34 and 38).
Therefore, it would have been obvious to combine Wang with Aluru to obtain the invention as specified in claim 17.
Regarding claim 36, Aluru discloses the method of claim 11, wherein the parametric distribution of the data is a point cloud data encoding (Fig. 4; paragraphs 29, 38-42, 66-67, wherein the parametric distribution is a 3D point cloud (fig. 4) encoded based on analysis of 2D images, and therefore corresponds to “a point cloud data encoding”).
Aluru does not disclose expressly wherein the point cloud data encoding is output to a downstream task that includes at least one of classification or segmentation.
Wang discloses a process of reconstructing a 3D point cloud from 2D images using a trained convolutional neural network (CNN), wherein the 3D point cloud is then used by, for example, doctors for diagnosis/classification of lesions for (Figs. 1, 2; paragraphs 05, 36-45).
Aluru & Wang are combinable because they are from the same art of processing 2D images to reconstruct a 3D point cloud.
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to incorporate the technique of using a 3D point cloud in the downstream task of classification, as taught by Wang, into the process for generating a 3D point cloud disclosed by Aluru.
The suggestion/motivation for doing so would have been to provide accurate visual information allowing for better decision making (Wang, paragraph 05).
Therefore, it would have been obvious to combine Wang with Aluru to obtain the invention as specified in claim 36.
Claims 33 and 34 are rejected under 35 U.S.C. 103 as being unpatentable over US 2023/0388470 to Aluru et al. (“Aluru”) in view of the article “Point Cloud Attribute Compression with Graph Transform” to Zhang et al. (“Zhang”).
Regarding claim 33, Aluru discloses the method of claim 32, wherein the parametric distribution of the data is a blob (Fig. 4; paragraphs 29, 38-42, 66-67, wherein 3D point cloud data corresponds to the broadest reasonable interpretation of a “blob” of data (i.e. vague shape), as seen in figure 4).
Aluru does not disclose expressly wherein the parametric distribution of the data is a Gaussian blob.
Zhang discloses a process that comprises representing a 3D point cloud (i.e. parametric distribution of data) as a Gaussian distribution/blob (Section 2.1).
Aluru & Zhang are combinable because they are from the same art of 3D point cloud processing.
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to incorporate the technique of representing a 3D point cloud (i.e. parametric distribution of data) as a Gaussian blob, as taught by Zhang, into the process for learning and outputting a 3D point cloud as disclosed by Aluru.
The suggestion/motivation for doing so would have been to provide the point cloud in a matrix/distribution that effectively compacts the energy of the signal (Zhang, section 2.1, last paragraph).
Therefore, it would have been obvious to combine Zhang with Aluru to obtain the invention as specified in claim 33.
Regarding claim 34, Aluru discloses the method of claim 32, wherein the parametric distribution of the data is a blob (Fig. 4; paragraphs 29, 38-42, 66-67, wherein 3D point cloud data corresponds to the broadest reasonable interpretation of a “blob” of data (i.e. vague shape), as seen in figure 4).
Aluru does not disclose expressly wherein the parametric distribution of the data is a Laplacian blob.
Zhang discloses a process that comprises representing a 3D point cloud (i.e. parametric distribution of data) as a Laplacian distribution/blob (Section 3.1).
Aluru & Zhang are combinable because they are from the same art of 3D point cloud processing.
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to incorporate the technique of representing a 3D point cloud (i.e. parametric distribution of data) as a Laplacian blob, as taught by Zhang, into the process for learning and outputting a 3D point cloud as disclosed by Aluru.
The suggestion/motivation for doing so would have been to provide the point cloud distribution that allows for significant improvement when encoding attributes (Zhang, section 5, first paragraph).
Therefore, it would have been obvious to combine Zhang with Aluru to obtain the invention as specified in claim 34.
Allowable Subject Matter
Claims 1-10 are allowed.
Claims 18-31, 38, 40, 41, 44 and 45 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is an examiner’s statement of reasons for allowance:
Regarding claim 1, none of the prior art teach or fairly suggests the limitations of:
“providing to each layer of the plurality of densely connected layers the input of the dimensionality that the layer is configured to process, at each layer of the plurality of densely connected layers computing from the provided input a dimension-wise transformation for each of a plurality of kernels, wherein the computing across the plurality of densely connected layers is performed in parallel, applying a non-linear activation to a result of each of the dimension-wise transformations computed across the plurality of densely connected layers to generate a modified dimension-wise transformation result, and for each kernel of the plurality of kernels, aggregating the modified dimension-wise transformation results computed across the plurality of densely connected layers to generate a single output for the kernel”.
The prior art of Aluru (US2023/0388470) discloses a process for implicitly learning a point cloud data encoding. However, neither Aluru nor any other prior art found teach or fairly suggests the above limitations.
Any comments considered necessary by applicant must be submitted no later than the payment of the issue fee and, to avoid processing delays, should preferably accompany the issue fee. Such submissions should be clearly labeled “Comments on Statement of Reasons for Allowance.”
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See attached PTO-892.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AARON W CARTER whose telephone number is (571)272-7445. The examiner can normally be reached 8am - 5pm (Mon - Fri).
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, John Villecco can be reached at (571) 272-7319. 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.
/AARON W CARTER/Primary Examiner, Art Unit 2661
Prosecution Insights