CTNF 18/798,017 CTNF 99321 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Priority Receipt is acknowledged that application is a National Stage application of PCT PCT/KR2023/001805. Priority to INDIA 202241006700 with a priority date of 02/08/2022 is acknowledged under 35 USC 119(e) and 37 CFR 1.78. Information Disclosure Statement The IDS(s) dated 04/09/2026, 02/06/2025, and 08/08/2024 has been considered and placed in the application file. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-23-aia AIA The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows: 1. Determining the scope and contents of the prior art. 2. Ascertaining the differences between the prior art and the claims at issue. 3. Resolving the level of ordinary skill in the pertinent art. 4. Considering objective evidence present in the application indicating obviousness or nonobviousness. Claim(s) 1, 3-8, and 10-18 is/are rejected under 35 U.S.C. 103 as obvious over Tripathi et al ("Learning to Generate Synthetic Data via Compositing", hereafter referred to as Tripathi) in view of Fang et al ("InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting", hereafter referred to as Fang). Claim 1 Regarding Claim 1 , Tripathi teaches A method for controlling an electronic device, the method comprising: obtaining one or more artifact free images (Tripathi in Section 3 discloses “Our approach for generating hard training examples through image composition requires as input a background image, b ”.) and one or more artifacts represented by one or more artifact masks (Tripathi in Section 3 discloses “Our approach for generating hard training examples through image composition requires as input … a segmented foreground object mask, m , from the object classes of interest”.) ; generating one or more transformed artifact masks by applying at least one localization parameter amongst a plurality of localization parameters to the one or more artifact masks (Tripathi in Section 3.1 discloses “given a background image b and foreground mask m , the synthesizer outputs a 6-dimentsional affine transformation vector A . A Spatial Transformer module applies A to m”. ) ; generating one or more artifact images by combining the one or more artifact free images and the one or more localized artifact masks (Tripathi in Section 3.1 discloses “[producing] a composite synthetic image, f = b ⊕ A(m), where ⊕ denotes the alpha blending [26] operation”) . Tripathi does not explicitly teach all of obtaining a region of interest (ROI) mask identifying one or more ROIs in the one or more artifact free images; generating one or more localized artifact masks by placing the one or more transformed artifact masks on the ROI mask. However, Fang teaches obtaining a region of interest (ROI) mask identifying one or more ROIs in the one or more artifact free images (Fang in Abstract discloses “Furthermore, we propose a location probability map based approach to explore the feasible locations that objects can be placed based on local appearance similarity. With the guidance of such map, we boost the performance of R101-Mask R-CNN on instance segmentation from 35.7 mAP to 37.9 mAP”; Section 3.1 discloses “we define prob ability density function f(·) measuring how reasonable it is to paste the object O on the given image I, following a specific transformation tuple.”; Section 3.3.1 discloses “Appearance distances are normalized and scaled via negative log for the heatmap H”; See also Figure 5.) ; generating one or more localized artifact masks by placing the one or more transformed artifact masks on the ROI mask (Fang in Section 3.3.1 discloses “Appearance distances are normalized and scaled via negative log for the heatmap H”; Section 3.3.2 discloses “heatmap values are proportional to the probability density function on x,y-axis … Therefore, values in the appearance consistency heatmap are normalized and treated as probabilities, from which candidate points are sampled via Monte Carlo method”; Section 3.1 discloses “we define probability density function f(·) measuring how reasonable it is to paste the object O on the given image I, following a specific transformation tuple.”). Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Tripathi by incorporating ROI-guided placement that is taught by Fang , since both reference are analogous art in the field of synthetic data generation; thus, one of ordinary skilled in the art would be motivated to combine the references since Tripathi’s framework for generating synthetic training data by composting transformed foreground masks onto background images with Fang’s context-aware region identification yields the predictable result of constraining object/artifact placement to semantically appropriate regions. Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention. Claim 3 Regarding Claim 3, Tripathi in view of Fang teaches The method as claimed in claim 1, further comprising: analyzing the one or more artifact images (Tripathi in Section 1 discloses “goal of the target network is to correctly classify/detect all instances of foreground object in the composite images”) to detect a presence of the one or more artifacts represented by the one or more localized artifact masks in the one or more artifact images (Tripathi in Section 3.2 discloses T classifies the foreground object in the composite) ; determining that the one or more artifacts represented by the one or more localized artifact masks is present in the one or more artifact images (Tripathi in Section 3.2 discloses T is optimized to minimize classification loss. The target network produces classification scores for object categories at anchor locations in the composite image) ; and producing the one or more artifact images comprising the one or more artifacts represented by the one or more localized artifact masks as an output (Tripathi in Section 3 and 3.1 discloses “a 3-way competition among the synthesizer S, the target T , and the discriminator D … [producing] a composite synthetic image, f = b ⊕ A(m)”, where f is the output artifact image containing the composited artifact) . Claim 4 Regarding Claim 4, Tripathi in view of Fang teaches The method as claimed in claim 1, further comprising: providing feedback (Tripathi in Section 3 discloses “a 3-way competition among the synthesizer S, the target T , and the discriminator D”; Section 3.4 discloses “For a given training batch, parameters of S are updated while keeping parameters of T and D fixed. Similarly, parameters of T and D are updated by keeping parameters of S fixed.”) for varying one of the plurality of localization parameters (Tripathi in Section 3.4 discloses objective function (3) where S optimizes its outputs, including the 6-D affine transformation vector A, based on feedback) and one or more illumination parameters (Tripathi in Section 3.4 discloses S receives feedback to generate harder examples) in response to determining that the one or more artifacts represented by the one or more localized artifact masks is absent in the one or more artifact images (Tripathi in Section 3.4 discloses when the target network fails to classify/detect the composited foreground, the adversarial feedback causes S to update its parameters to generate better examples that T can detect) . Claim 5 Regarding Claim 5, Tripathi in view of Fang teaches The method as claimed in claim 1, wherein the obtaining the ROI mask comprises: obtaining, from the one or more artifact free images, one or more segmentation masks of one or more categories (Fang in Section 3.3.1 discloses “we define the appearance descriptor D(·) as the weighted combination of three fixed width contour areas with different scales, which can be formulated as” Equation (7); Section 4.2 discloses COCO (80 categories) and VOC (20 categories)) depicting contextual information associated with the plurality of ROIs (Fang in Section 3.3.1 discloses the contour masks encode contextual information (appearance/texture similarity) that determines where ROIs are located) ; and obtaining the ROI mask based on the one or more segmentation masks of the one or more categories (Fang in Section 3.3.1 discloses distances are normalized and mapped to a heatmap where high values indicate a strong appearance consistency. The heatmap is the ROI mask computed entirely from the segmentation based contour masks) . Claim 6 Regarding Claim 6, Tripathi in view of Fang teaches The method as claimed in claim 1, wherein the plurality of localization parameters is determined based on: computing a size and dimensions associated with the ROI mask (Fang in Section 3.1 discloses “Given a cropped object patch from a specific image, the placement of that patch on the image can be defined by the affine transformation matrix … tx, ty denote the coordinate shift in x,y-axis respectively, s denotes the scale variance”) ; and adjusting a plurality of pre-defined localization parameters of the one or more artifact masks according to the size and the dimensions of the ROI mask (Fang in Section 3.1 discloses “Given a cropped object patch from a specific image, the placement of that patch on the image can be defined by the affine transformation matrix … s denotes the scale variance”; scale is adjusted relative to the placement context defined by the probability map. (Tripathi in Section 3.1 discloses a 6-dimentsional affine transformation vector A where the scale parameter is a pre-defined localization parameter) and generating the plurality of localization parameters (Fang in Section 3.3.2 discloses the coordinate shifts (tx, ty) are generated based on the heatmap’s size and regions) . Claim 7 Regarding Claim 7, Tripathi in view of Fang teaches The method as claimed in claim 6, further comprising: varying the plurality of pre-defined localization parameters of the artifact mask within a range (Fang in 3.3.2 discloses each sampling draws different parameter values within a defined range) to generate at least one other set of plurality of localization parameters (Fang in discloses multiple Monte Carlo drawn from the same distribution produce multiple distinct parameter sets) ; applying the at least one other set of the plurality of localization parameters on the one or more artifact masks to generate at least one other transformed artifact mask (Tripathi in Section 3.1 discloses each distinct A (6-D vector) applied to m produces a distinct A(m) (transformed mask). Different parameters equal different transformed masks) ; and generating at least one other localized artifact mask by placing the at least one other transformed artifact mask on the ROI mask (Fang in 3.3.2 discloses each Monte Carlo sample places the transformed instance at a new (tx, ty) location on the heatmap/background. Different samples equals different localized artifact masks) for further generating at least one other artifact image (Tripathi in discloses “f = b ⊕ A(m)” where each distinct A produces a distinct composite image f) . Claim 8 Regarding Claim 8, Tripathi in view of Fang teaches The method as claimed in claim 1, wherein the plurality of localization parameters comprises at least one of a translation, a rotation, a shear, a flip, and a scaling associated with the one or more artifact masks (Tripathi in Section 3.4 discloses “a 6−dimensional feature vector representing the affine transformation parameters”. (Fang in Section 3.1 discloses “s denotes the scale variance”)) . Claim 10 Regarding Claim 10, Tripathi in view of Fang teaches The method as claimed in claim 1, wherein the one or more artifact free images capture an object, a scene, and a living being (Tripathi in Figure 5 discloses objects, a scene, and a living being) . Claim 11 Regarding Claim 11, Tripathi in view of Fang teaches The method as claimed in claim 1, wherein the one or more artifacts represented by the one or more artifact masks and the one or more artifact free images are pre-stored in the electronic device (Tripathi in Section 3 discloses “Our approach for generating hard training examples through image composition requires as input a background image, b, and a segmented foreground object mask, m, from the object classes of interest”) . Claim 12 Regarding Claim 12 , Tripathi teaches An electronic device comprising: a memory storing one or more instructions (Tripathi in Abstract discloses “a task-aware approach to synthetic data generation”) ; and a processor (Tripathi in Abstract discloses “a task-aware approach to synthetic data generation”) configured to execute the one or more instructions to: obtain, from the memory, one or more artifact free images (Tripathi in Section 3 discloses “Our approach for generating hard training examples through image composition requires as input a background image, b ”.) and one or more artifacts represented by one or more artifact masks (Tripathi in Section 3 discloses “Our approach for generating hard training examples through image composition requires as input … a segmented foreground object mask, m , from the object classes of interest”.) ; generate one or more transformed artifact masks by applying at least one localization parameter amongst a plurality of localization parameters to the one or more artifact masks (Tripathi in Section 3.1 discloses “given a background image b and foreground mask m , the synthesizer outputs a 6-dimentsional affine transformation vector A . A Spatial Transformer module applies A to m”. ) ; generate one or more artifact images by combining the one or more artifact free images and the one or more localized artifact masks (Tripathi in Section 3.1 discloses “[producing] a composite synthetic image, f = b ⊕ A(m), where ⊕ denotes the alpha blending [26] operation”) . Tripathi does not explicitly teach all of obtaining a region of interest (ROI) mask identifying one or more ROIs in the one or more artifact free images; generate one or more localized artifact masks by placing the one or more transformed artifact masks on the ROI mask. However, Fang teaches obtaining a region of interest (ROI) mask identifying one or more ROIs in the one or more artifact free images (Fang in Abstract discloses “Furthermore, we propose a location probability map based approach to explore the feasible locations that objects can be placed based on local appearance similarity. With the guidance of such map, we boost the performance of R101-Mask R-CNN on instance segmentation from 35.7 mAP to 37.9 mAP”; Section 3.1 discloses “we define prob ability density function f(·) measuring how reasonable it is to paste the object O on the given image I, following a specific transformation tuple.”; Section 3.3.1 discloses “Appearance distances are normalized and scaled via negative log for the heatmap H”; See also Figure 5.) ; generate one or more localized artifact masks by placing the one or more transformed artifact masks on the ROI mask (Fang in Section 3.3.1 discloses “Appearance distances are normalized and scaled via negative log for the heatmap H”; Section 3.3.2 discloses “heatmap values are proportional to the probability density function on x,y-axis … Therefore, values in the appearance consistency heatmap are normalized and treated as probabilities, from which candidate points are sampled via Monte Carlo method”; Section 3.1 discloses “we define probability density function f(·) measuring how reasonable it is to paste the object O on the given image I, following a specific transformation tuple.”). Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Tripathi by incorporating ROI-guided placement that is taught by Fang , since both reference are analogous art in the field of synthetic data generation; thus, one of ordinary skilled in the art would be motivated to combine the references since Tripathi’s framework for generating synthetic training data by composting transformed foreground masks onto background images with Fang’s context-aware region identification yields the predictable result of constraining object/artifact placement to semantically appropriate regions. Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention. Claim 14 Regarding Claim 14, Tripathi in view of Fang teaches The electronic device as claimed in claim 12, wherein the processor is further configured to: analyze the one or more artifact images (Tripathi in Section 1 discloses “goal of the target network is to correctly classify/detect all instances of foreground object in the composite images”) to detect a presence of the one or more artifacts represented by the one or more localized artifact masks in the one or more artifact images (Tripathi in Section 3.2 discloses T classifies the foreground object in the composite) ; determine that the one or more artifacts represented by the one or more localized artifact masks is present in the one or more artifact images (Tripathi in Section 3.2 discloses T is optimized to minimize classification loss. The target network produces classification scores for object categories at anchor locations in the composite image) ; and produce the one or more artifact images comprising the one or more artifacts represented by the one or more localized artifact masks as an output (Tripathi in Section 3 and 3.1 discloses “a 3-way competition among the synthesizer S, the target T , and the discriminator D … [producing] a composite synthetic image, f = b ⊕ A(m)”, where f is the output artifact image containing the composited artifact) . Claim 15 Regarding Claim 15, Tripathi in view of Fang teaches The electronic device as claimed in claim 12, wherein the processor is further configured to: provide feedback (Tripathi in Section 3 discloses “a 3-way competition among the synthesizer S, the target T , and the discriminator D”; Section 3.4 discloses “For a given training batch, parameters of S are updated while keeping parameters of T and D fixed. Similarly, parameters of T and D are updated by keeping parameters of S fixed.”) for varying one of the plurality of localization parameters (Tripathi in Section 3.4 discloses objective function (3) where S optimizes its outputs, including the 6-D affine transformation vector A, based on feedback) and one or more illumination parameters (Tripathi in Section 3.4 discloses S receives feedback to generate harder examples) in response to determining that the one or more artifacts represented by the one or more localized artifact masks is absent in the one or more artifact images (Tripathi in Section 3.4 discloses when the target network fails to classify/detect the composited foreground, the adversarial feedback causes S to update its parameters to generate better examples that T can detect) . Claim 16 Regarding Claim 16 , Tripathi teaches A non-transitory computer-readable storage medium storing a program that is executable by a processor to perform a method of controlling an electronic device, the method comprising obtaining an artifact free image (Tripathi in Section 3 discloses “Our approach for generating hard training examples through image composition requires as input a background image, b ”.) and an artifact mask identifying an artifact (Tripathi in Section 3 discloses “Our approach for generating hard training examples through image composition requires as input … a segmented foreground object mask, m , from the object classes of interest”.) ; obtaining a localized artifact mask by applying at least one localization parameter to the artifact mask (Tripathi in Section 3.1 discloses “[producing] a composite synthetic image, f = b ⊕ A(m), where ⊕ denotes the alpha blending [26] operation”) and adjusting a position of the artifact mask to overlap with a region of interest (ROI) included in the artifact free image ; and obtaining an artifact image by combining the artifact free image with the localized artifact mask (Tripathi in Section 3.1 discloses “[producing] a composite synthetic image, f = b ⊕ A(m), where ⊕ denotes the alpha blending [26] operation”) . Tripathi does not explicitly teach all of adjusting a position of the artifact mask to overlap with a region of interest (ROI) included in the artifact free image. However, Fang teaches adjusting a position of the artifact mask to overlap with a region of interest (ROI) included in the artifact free image (Fang in Section 3.3.1 discloses “Appearance distances are normalized and scaled via negative log for the heatmap H”; Section 3.3.2 discloses “heatmap values are proportional to the probability density function on x,y-axis … Therefore, values in the appearance consistency heatmap are normalized and treated as probabilities, from which candidate points are sampled via Monte Carlo method”; Section 3.1 discloses “we define probability density function f(·) measuring how reasonable it is to paste the object O on the given image I, following a specific transformation tuple.”). Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Tripathi by incorporating ROI-guided placement that is taught by Fang , since both reference are analogous art in the field of synthetic data generation; thus, one of ordinary skilled in the art would be motivated to combine the references since Tripathi’s framework for generating synthetic training data by composting transformed foreground masks onto background images with Fang’s context-aware region identification yields the predictable result of constraining object/artifact placement to semantically appropriate regions. Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention. Claim 17 Regarding Claim 17, Tripathi in view of Fang teaches The non-transitory computer-readable storage medium as claimed in claim 16, wherein the at least one localization parameter comprises at least one of a translation, a rotation, a shear, a flip, and a scaling associated with the artifact mask (Tripathi in Section 3.4 discloses “a 6−dimensional feature vector representing the affine transformation parameters”. Fang in Section 3.1 discloses “s denotes the scale variance”) . Claim 18 Regarding Claim 18, Tripathi in view of Fang teaches The non-transitory computer-readable storage medium as claimed in claim 16, wherein the method further comprises: determining the at least one localization parameter based on a size and a dimension of the ROI (Fang in Section 3.1 discloses “Given a cropped object patch from a specific image, the placement of that patch on the image can be defined by the affine transformation matrix … s denotes the scale variance”; scale is adjusted relative to the placement context defined by the probability map; Section 3.3.2 discloses the coordinate shifts (tx, ty) are generated based on the heatmap’s size and regions. Tripathi in Section 3.1 discloses a 6-dimentsional affine transformation vector A where the scale parameter is a pre-defined localization parameter). Claim(s) 2 and 13 is/are rejected under 35 U.S.C. 103 as obvious over Tripathi et al ("Learning to Generate Synthetic Data via Compositing", hereafter referred to as Tripathi) in view of Fang et al ("InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting", hereafter referred to as Fang), further in view of Cubuk et al ("AutoAugment: Learning Augmentation Strategies from Data", hereafter referred to as Cubuk). Claim 2 Regarding Claim 2 , Tripathi in view of Fang teaches The method as claimed in claim 1; wherein the generating the one or more artifact images comprises: generating the one or more artifact images by combining the one or more artifact free images, the one or more localized artifact masks and the one or more varied intensity images (Tripathi in Section 3.1 discloses “[producing] a composite synthetic image, f = b ⊕ A(m)” where b is the background and A(m) is the transformed mask. The varied intensity version of b is substituted as the base image and combined with A(m) via alpha blending) . Tripathi in view of Fang does not explicitly teach all of generating one or more varied intensity images by applying one or more illumination parameters to the one or more artifact free images. However, Cubuk teaches generating one or more varied intensity images (Cubuk in Section 3 discloses each operation (brightness, contrast, color) produces a version of the image with modified intensity. AutoAugment applies these randomly per mini-batch at varying magnitudes.) by applying one or more illumination parameters (Cubuk in Section 3 discloses “In total, we have 16 operations in our search space … Contrast, Color, Brightness”) to the one or more artifact free images (Cubuk in Section 3 discloses AutoAugment applies operations to training images before they are fed to the network). Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Tripathi in view of Fang by incorporating photometric augmentation that is taught by Cubuk , since both reference are analogous art in the field of synthetic data generation; thus, one of ordinary skilled in the art would be motivated to combine the references since Tripathi in view of Fang’s ROI-guided compositing pipeline with Cubuk’s photometric augmentations yields the predictable result of producing more training sample diversity. Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention. Claim 13 Regarding Claim 13 , Tripathi in view of Fang teaches The electronic device as claimed in claim 12, wherein the processor is further configured to: generate the one or more artifact images by combining the one or more artifact free images, the one or more localized artifact masks and the one or more varied intensity images (Tripathi in Section 3.1 discloses “[producing] a composite synthetic image, f = b ⊕ A(m)” where b is the background and A(m) is the transformed mask. The varied intensity version of b is substituted as the base image and combined with A(m) via alpha blending) . Tripathi in view of Fang does not explicitly teach all of generate one or more varied intensity images by applying one or more illumination parameters to the one or more artifact free images. However, Cubuk teaches generate one or more varied intensity images (Cubuk in Section 3 discloses each operation (brightness, contrast, color) produces a version of the image with modified intensity. AutoAugment applies these randomly per mini-batch at varying magnitudes.) by applying one or more illumination parameters (Cubuk in Section 3 discloses “In total, we have 16 operations in our search space … Contrast, Color, Brightness”) to the one or more artifact free images (Cubuk in Section 3 discloses AutoAugment applies operations to training images before they are fed to the network). Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Tripathi in view of Fang by incorporating photometric augmentation that is taught by Cubuk , since both reference are analogous art in the field of synthetic data generation; thus, one of ordinary skilled in the art would be motivated to combine the references since Tripathi in view of Fang’s ROI-guided compositing pipeline with Cubuk’s photometric augmentations yields the predictable result of producing more training sample diversity. Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention. Claim(s) 9 is/are rejected under 35 U.S.C. 103 as obvious over Tripathi et al ("Learning to Generate Synthetic Data via Compositing", hereafter referred to as Tripathi) in view of Fang et al ("InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting", hereafter referred to as Fang), further in view of Hong et al ("Shadow Generation for Composite Image in Real-World Scenes", hereafter referred to as Hong). Claim 9 Regarding Claim 9 , Tripathi in view of Fang teaches The method as claimed in claim 1. Tripathi in view of Fang does not explicitly teach all of wherein the one or more artifact comprises a region of shadow casted by one or more of an object, a scene, and a living being and the one or more artifact masks represent a location of the one or more artifacts in the image using a binary mask image . However, Hong teaches wherein the one or more artifact comprises a region of shadow casted by one or more of an object, a scene, and a living being (Hong in Figure 1 discloses identifying a shadow region) and the one or more artifact masks represent a location of the one or more artifacts in the image using a binary mask image (Hong in 4.1 discloses “The shadow mask generator GS aims to predict the binary shadow mask Mfs of the foreground object ” ) . Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Tripathi in view of Fang by incorporating shadow-specific masks that is taught by Hong , since both reference are analogous art in the field of synthetic data generation; thus, one of ordinary skilled in the art would be motivated to combine the references since Tripathi in view of Fang’s ROI-guided compositing pipeline with Hong’s shadow-specific masks yields the predictable result of generating realistic image composites. Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to JUSTIN P CASCAIS whose telephone number is (703) 756-5576. The examiner can normally be reached Monday-Friday 8:00-4:00. 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, Mr. O'Neal Mistry can be reached on (313) 446-4912. 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. /J.P.C./Examiner, Art Unit 2674 /ONEAL R MISTRY/Supervisory Patent Examiner, Art Unit 2674 Date: 5/21/2026 Application/Control Number: 18/798,017 Page 2 Art Unit: 2674 Application/Control Number: 18/798,017 Page 3 Art Unit: 2674 Application/Control Number: 18/798,017 Page 4 Art Unit: 2674 Application/Control Number: 18/798,017 Page 5 Art Unit: 2674 Application/Control Number: 18/798,017 Page 6 Art Unit: 2674 Application/Control Number: 18/798,017 Page 7 Art Unit: 2674 Application/Control Number: 18/798,017 Page 8 Art Unit: 2674 Application/Control Number: 18/798,017 Page 9 Art Unit: 2674 Application/Control Number: 18/798,017 Page 10 Art Unit: 2674 Application/Control Number: 18/798,017 Page 11 Art Unit: 2674 Application/Control Number: 18/798,017 Page 12 Art Unit: 2674
Prosecution Insights