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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 6/22/2026 was filed after the mailing date of the Non-Final Office action on 11/21/2025. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Amendment
This Office action is in response to Applicant’s argument filed 3/23/2026. Applicant's request for reconsideration of the rejection of the last Office action is persuasive and, therefore, the finality of that action is withdrawn.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-3, 5-6 and 11-20 are rejected under 35 U.S.C. 103 as being unpatentable over Choi et al. (US 20220051017 A1, hereinafter Choi) in view of Abbeloos et al. (WO 2023/186262 A1, hereinafter Abbeloos).
Regarding claim 1, Choi discloses a method comprising: accessing a feature map (figure 2, 206), wherein the feature map is generated by a preceding set of neural network layers ([0067], object detections layer 108 detects one or more objects in one or more feature maps and object detections layer 108 comprises one or more neural networks that generate probability distributions indicating potential locations and classifications of objects in an image); reconstructing a set of local points with a first neural network by using the feature map ([0068]-[0072], object detections layer 108 processes each location of each feature map output by convolutional layers 106 and object detections layer 108 models each coordinate of said bounding box as a Gaussian Mixture Model for each bounding box). Choi differs from the claimed invention in not specifically disclosing the steps of estimating a six-dimensional (6D) pose with a second neural network by using the feature map; transforming, by the estimated 6D pose, each local coordinate extracted from the set of local points; and outputting the reconstructed point cloud. However, Abbeloos teaches a method to obtain a final 6D pose of the camera of the first image for optimizing the final 6D pose using the reference pose of the camera used to acquire the reference image comprising the steps of estimating a six-dimensional (6D) pose with a second neural network by using the feature map (page 21 lines 13-30, F.sub.query designates an image processing neural network feature in the image for which the pose is to be determined); transforming, by the estimated 6D pose, each local coordinate extracted from the set of local points (page 22 lines 1-14, an additional image processing neural network is trained for the image/the query image during the training phase to modify the error by considering the difference between the feature from the reference image at the projection in the reference image of the point in the point cloud with the reference pose associated with the point cloud and the reference image, i.e., the pose of the camera to acquire the reference image, obtained with this point cloud, and the feature from the query image at the projection in the query image with the pose between the point cloud and the query image, i.e., this pose is predicted); and outputting the reconstructed point cloud (page 26 lines 22-26, the feature in the feature map at the pixel location corresponding to the projection of this point of the point cloud on the image when the camera is at the initial 6D pose) in order to optimize the final 6D pose using the reference pose of the camera. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Choi in having the steps of estimating a six-dimensional (6D) pose with a second neural network by using the feature map; transforming, by the estimated 6D pose, each local coordinate extracted from the set of local points; and outputting the reconstructed point cloud, as per teaching of Abbeloos, in order to optimize the 6D pose.
Regarding claim 2, Choi differs from the claimed invention in not specifically teaching that the feature map is a block feature map, wherein estimating the 6D pose comprises estimating the 6D pose on a per block basis, and wherein transforming each extracted local coordinate comprises transforming the 6D pose on a per block basis. Abbeloos teaches, and the a block is a set of layers and connections, which receives features as input and outputs features neural network can comprise multiple blocks and it is possible to assign a level to any position to extract features at a plurality of positions such that 6D pose is expressed using the SE(3) group, by a rotation R and a translation t. (page 9 line 25 through page 11 line 12) to acquire the image of the scene using the point cloud processing neural network in an effective manner. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Choi in having that the feature map is a block feature map, wherein estimating the 6D pose comprises estimating the 6D pose on a per block basis, and wherein transforming each extracted local coordinate comprises transforming the 6D pose on a per block basis, as per teaching of Abbeloos, in order to acquire the image of the scene using the point cloud processing neural network in an effective manner.
Regarding claim 3, Choi teaches that the first neural network is a learning-based surface reconstruction-type neural network ([0548], an image reconstruction application may include a processing task that includes use of a machine learning model).
Regarding claim 5, Choi differs from the claimed invention in not specifically teaching the step of estimating the 6D pose comprises: estimating, for each block of the plurality of blocks associated with the feature map, an array of translational matrices; and estimating, for each block of a plurality of blocks associated with the feature map, an array of rotational matrices. However, Abbeloos teaches image processing neural network delivers a plurality of feature maps, each associated with a level of the neural network such that aligning image features and point cloud features Fp by finding the optimal camera pose parameters as a rotation R and a translation t (page 3 lines 13-17 and page 13 lines 12-28). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Choi in having that the step of estimating the 6D pose comprises: estimating, for each block of the plurality of blocks associated with the feature map, an array of translational matrices; and estimating, for each block of a plurality of blocks associated with the feature map, an array of rotational matrices, as per teaching of Abbeloos, in order to acquire the image of the scene using the point cloud processing neural network in an effective manner.
Regarding claim 6, Choi differs from the claimed invention in not specifically teaching that transforming each local coordinate extracted from the set of local points comprises: translating at least one of the local points using the array of translational matrices; and rotating at least one of the local points using the array of rotational matrices. However, Abbeloos teaches that the input, where the depth d is constant for every block and anchor points for each block, and the k-nearest neighbors are then computed in what is an MLP block which aggregates local features and outputs the final point-wise features (page 10 line 20 through page 11 line 2 and page 14 lines 1-20). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Choi in having that transforming each local coordinate extracted from the set of local points comprises: translating at least one of the local points using the array of translational matrices; and rotating at least one of the local points using the array of rotational matrices, as per teaching of Abbeloos, in order to acquire the image of the scene using the point cloud processing neural network in an effective manner.
Regarding claims 11-12, Choi differs from the claimed invention in not specifically teaching that estimating the array of translational matrices comprises using a translation estimation process, and estimating the array of rotational matrices comprises using a rotation estimation process. However, Abbeloos teaches point cloud features Fp by finding the optimal camera pose parameters as a rotation R and a translation t, i.e., with K being the camera's intrinsic matrix, the projection of a point p, in 3d world coordinates, to a point q in image coordinates is given as equation 1, such that estimating the array of translational matrices comprises using a translation estimation process, and estimating the array of rotational matrices comprises using a rotation estimation process (page 13 line 20 through page 14 line 14). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Choi in having that estimating the array of translational matrices comprises using a translation estimation process, and estimating the array of rotational matrices comprises using a rotation estimation process, as per teaching of Abbeloos, in order to acquire the image of the scene using the point cloud processing neural network in an effective manner.
Regarding claim 13, Choi teaches performing a dimensionality reduction technique ([0066], convolutional layers 106 reduce sizes of feature maps output from feature extraction layer 104).
Regarding claim 14, Choi discloses entropy decoding a bitstream to generate the feature map ([0098], feature maps of various sizes and resolutions are generated from input image through one or more convolutional operations and/or layers).
Regarding claims 15-16, Choi discloses performing a feature aggregation process on the feature map, wherein the feature aggregation process comprises: performing at least one convolutional layer process; and performing at least one rectifier linear unit (ReLU) process ([0085], overall maximum uncertainty values are aggregated to determine an informativeness score through determining an average of said values, in which said average indicates said informativeness score, and an informativeness score for input image 102 indicates how uncertain a deep object detection network is at identifying and classifying objects of input image 102, in which a higher informativeness score indicates a higher uncertainty.).
Regarding claim 17, the limitations of the claim are rejected as the same reasons as set forth in claim 1.
Regarding claim 18, the limitations of the claim are rejected as the same reasons as set forth in claims 1 and 14.
Regarding claim 19, , the limitations of the claim are rejected as the same reasons as set forth in claim 2.
Regarding claim 20, , the limitations of the claim are rejected as the same reasons as set forth in claim 3.
Allowable Subject Matter
Claims 4 and 7-10 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 a statement of reasons for the indication of allowable subject matter: The prior art of record fails to teach nor suggest “wherein reconstructing the set of local points comprises: selecting a first set from a group of grid points; repeating a loop based on a quantity of points in the feature map: concatenating the first set and a subset of a block feature vector to generate a concatenated set of points; and passing the concatenated set of points through the first neural network to generate the first set for a next pass through the loop; and outputting, as the set of local points, the first set from a last pass through the loop” as recited in claim 4; “wherein transforming each local coordinate extracted from the set of local points comprises: re-centering, using the array of translational matrices, at least one of the local points; and aligning, using the array of rotational matrices, at least of the local points “ as recited in claim 7; “determining a loss function using at least one of the array of translational matrices and the array of rotational matrices” as recited in claim 8; “estimating the array of translational matrices comprises: performing at least one convolutional layer process on the feature map; and performing at least one multi-layer perceptron (MLP) process on an output of the at least one convolutional layer process to output the array of translational matrices” as recited in claim 9”; and “wherein estimating the array of rotational matrices comprises: performing at least one convolutional layer process on the feature map; and performing at least one multi-layer perceptron (MLP) process on an output of the at least one convolutional layer process to output the array of rotational matrices” as recited in claim 10.
Response to Arguments
Applicant’s arguments with respect to claims 1-20 3, 5-6 and 11-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Irshad et al. (US 2023/0077856 A1) discloses a 6D pose and size estimator system perform multi-object 3D shape reconstruction and categorical 6D pose and size estimation in a single-shot approach in a bounding-box free and per-pixel manner (abstract and [0015]-[0019]).
Meier et al. (US 11,335,024 B1) discloses a method for processing an image include inputting the image to a neural network configured to: obtain a plurality of feature maps, each feature map having a respective resolution and a respective depth, perform a classification on each feature map to deliver, for each feature map: the type of at least one object visible on the image, the position and shape in the image of at least one two-dimensional bounding box surrounding the at least one object, at least one possible viewpoint for the at least one object, at least one possible in-plane rotation for the at least one object (abstract and figure 1).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GEORGE ENG whose telephone number is (571)272-7495. The examiner can normally be reached Flex M to F, 7 am to 3 pm.
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, James A Kramer can be reached at (571) 272-6783. 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.
/GEORGE ENG/Supervisory Patent Examiner, Art Unit 2699
Prosecution Insights