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 .
Response to Arguments
Applicant's arguments filed 6 April 2026 have been fully considered but they are not persuasive.
Claims 1-16 are pending in this application and have been considered below. Claims 17-20 were not elected and are withdrawn from consideration.
Argument:
The applicant argues that Somanath does not teach or suggest "the feature data represents the pixels within the input image as a multi-resolution feature vector in a feature space" and further does not teach or suggest "applying, in the feature space, an offset to each pixel represented by the feature data based on per-pixel displacement vectors included in the predicted disparity map".
Response:
International Patent Publication WO 2013 109252 A1, (Somanath et al.) shows the limitation extracting feature data from the input image, wherein the feature data represents the pixels within the input image ("matching (for example, flow or feature-based) is performed for all pixels," Pg. 21, Line 3) as a multi-resolution feature vector in a feature space ("The features can be tracked using any tracking scheme, or comparing the feature vectors (descriptors) using either the L 1 or the L2 norm. The various detectors and descriptors vary in terms of invariance to image transformations (such as scale change), type of image features selected, and dimension of the descriptor. One or more implementations use any of a variety of these known techniques," Pg. 19, lines 2-7); and
applying, in the feature space ("As is known, given the dense depth map and the reference image, the corresponding stereo pair can be formed by using the depth map to obtain a disparity map, and then using the disparity map to form the stereo image for the reference image," Pg. 26, lines 5-8, where a dense depth map is a feature space), an offset to each pixel represented by the feature data based on per-pixel displacement vectors included in the predicted disparity map ("disparity map indicates the parallax/ horizontal shift for one or more pixels, and a dense disparity map typically indicates the parallax / horizontal shift for each pixel of the reference image," Pg. 26, Lines 6-10, where a disparity map is a feature space).
Priority
Applicant claims the benefit of US Provisional Application No. 63/503931, filed May 23, 2023. Claims 1-20 have been afforded the benefit of this filing date.
Information Disclosure Statement
The IDS dated 15 January 2025 has been considered and placed in the application file.
Election/Restrictions
Claims 17-20 are withdrawn from further consideration pursuant to 37 CFR 1.142(b), as being drawn to a nonelected Group, there being no allowable generic or linking claim.
Restriction to one of the following inventions was required under 35 U.S.C. 121:
I. Claims 1-16, drawn to a method and device for performing stereo conversion.
II. Claims 17-20, drawn to method for training a neural network.
The inventions are independent or distinct, each from the other because:
Inventions Ι and ΙΙ are directed to related processes. The related inventions are distinct if: (1) the inventions as claimed are either not capable of use together or can have a materially different design, mode of operation, function, or effect; (2) the inventions do not overlap in scope, i.e., are mutually exclusive; and (3) the inventions as claimed are not obvious variants. See MPEP § 806.05(j).
In the instant case, the inventions as claimed have different functions since invention Ι is creating a stereo image from a single image, and invention ΙΙ is training a machine learning model, with the only relation being the first limitation which states “executing a first neural network that predicts pixel-wise depth and disparity values associated with objects depicted in an input image.” And since statements of intended use have little patentable weight, the broadest reasonable interpretation of the limitation is very broad, the training method could apply to many neural networks having little to do with creating stereo images.
Restriction for examination purposes as indicated is proper because all the inventions listed in this action are independent or distinct for the reasons given above and there would be a serious search and/or examination burden if restriction were not required because one or more of the following reasons apply:
The inventions have acquired a separate status in the art in view of their different classification.
The inventions have acquired a separate status in the art due to their recognized divergent subject matter.
The inventions require a different field of search (different classes / subclasses and different search queries).
The prior art applicable to one invention would not likely be applicable to another invention.
The inventions are likely to raise different non-prior art issues under 35 USC 101 and 35 USC 112(a).
A telephone call was made to Sarah Mirza on 6 October 2025 to request an oral election to the above restriction requirement. Applicant timely traversed the restriction (election) requirement, electing claims 1-16 in the Oral reply filed on 8 October 2025.
1st Claim Interpretation
Under MPEP 2143.03, "All words in a claim must be considered in judging the patentability of that claim against the prior art." In re Wilson, 424 F.2d 1382, 1385, 165 USPQ 494, 496 (CCPA 1970). As a general matter, the grammar and ordinary meaning of terms as understood by one having ordinary skill in the art used in a claim will dictate whether, and to what extent, the language limits the claim scope. Language that suggests or makes a feature or step optional but does not require that feature or step does not limit the scope of a claim under the broadest reasonable claim interpretation. In addition, when a claim requires selection of an element from a list of alternatives, the prior art teaches the element if one of the alternatives is taught by the prior art. See, e.g., Fresenius USA, Inc. v. Baxter Int’l, Inc., 582 F.3d 1288, 1298, 92 USPQ2d 1163, 1171 (Fed. Cir. 2009).
Claims 4 and 19 recite “at least one of” then listing (claim 4) “a bounding box encompassing a portion of the input image, one or more brush strokes denoting portions of the input image, or a manual selection of an object depicted in the input image.” Since “at least one of” is disjunctive, any one of the elements found in the prior art is sufficient to reject the claim. While citations have been provided for completeness and rapid prosecution, only one element is required. Because, on balance, it appears the disjunctive interpretation enjoys the most specification support and for that reason the disjunctive interpretation (one of A, B OR C) is being adopted for the purposes of this Office Action. Applicant’s comments and/or amendments relating to this issue are invited to clarify the claim language and the prosecution history.
2nd Claim Interpretation
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification.
The following terms in the claims have been given the following interpretations in light of the specification:
Fully differentiable, Claim 6: paragraphs [0124], “All of the functions and transformations used by the stereo conversion engine are fully differentiable, which aids in end-to-end training of the underlying stereo conversion model via backpropagation. In operation, the stereo conversion engine performs disparity estimation on an input image by calculating pixel-wise inverse depth on a reduced resolution version of the input frame, and then performing an alignment step to yield disparity values, i.e., the per-point displacement vectors in pixels.”
Thus, a fully differentiable model is a neural network that can be trained with all parts at once. This definition is used for purposes of searching for prior art, but cannot be incorporated into the claims.
Should applicant wish different definitions, Applicant should point to the portions of the specification that clearly show a different definition.
1st Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (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.
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.
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.
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, 3-8, 11 and 13-14 are rejected under 35 U.S.C. 103 as obvious over International Patent Publication WO 2013 109252 A1, (Somanath et al.).
Claim 1
[AltContent: textbox (Somanath et al. Fig. 7, showing a method of stereo rendering an input video.)]
PNG
media_image1.png
607
578
media_image1.png
Greyscale
Regarding Claim 1, Somanath et al. teach a computer-implemented method for performing stereo conversion ("It is often desirable to create a stereoscopic image pair from a two-dimensional ("2D") image," Pg. 1, Lines 7-8), the computer-implemented method comprising:
generating, using one or more machine learning models, a predicted disparity map for an input image based on one or more depth values associated with pixels within the input image ("using the depth map to obtain a disparity map, and then using the disparity map to form the stereo image for the reference image," Pg. 26, Lines 6-8 and "divide the image into a fixed number of "super-pixels" page 21, lines 14-15, where super-pixels teach machine learning models);
extracting feature data from the input image , wherein the feature data represents the pixels within the input image ("matching (for example, flow or feature-based) is performed for all pixels," Pg. 21, Line 3)as a multi-resolution feature vector in a feature space ("The features can be tracked using any tracking scheme, or comparing the feature vectors (descriptors) using either the L 1 or the L2 norm. The various detectors and descriptors vary in terms of invariance to image transformations (such as scale change), type of image features selected, and dimension of the descriptor. One or more implementations use any of a variety of these known techniques," Pg. 19, lines 2-7);
applying, in the feature space ("As is known, given the dense depth map and the reference image, the corresponding stereo pair can be formed by using the depth map to obtain a disparity map, and then using the disparity map to form the stereo image for the reference image," Pg. 26, lines 5-8, where a dense depth map is a feature space), an offset to each pixel represented by the feature data based on per-pixel displacement vectors included in the predicted disparity map ("disparity map indicates the parallax/ horizontal shift for one or more pixels, and a dense disparity map typically indicates the parallax / horizontal shift for each pixel of the reference image," Pg. 26, Lines 6-10, where a disparity map is a feature space);
identifying a plurality of offset pixels represented by the feature data that are offset to a same pixel location ("left view 325 of the object is at the same horizontal position as the right view 327 of the object on the screen 320," Pg. 8, Lines 1-2);
assigning, based on the predicted disparity map, a visibility value to each of the plurality of offset pixels ("However, if d R is not substantially the same as -di_, then there may be an occlusion. For example, if the two disparity values are substantially different, after accounting for the sign, then there is generally a high degree of confidence that there is an occlusion," Pg. 11, Lines 12-15, where occlusion is a visibility value);
modifying, based on the visibility values, each of the plurality of offset pixels such that one of the plurality of offset pixels is visible and the others of the plurality of offset pixels are hidden ("Additionally, if one of the disparity values (either dR or dL) is unavailable, then there is generally a high degree of confidence that there is an occlusion. A disparity value may be unavailable because, for example, the disparity value cannot be determined. The occlusion generally 20 relates to one of the two images. For example, the portion of the scene shown by the pixel associated with the disparity having the smaller magnitude, or shown by the pixel corresponding to the unavailable disparity value, is generally considered to be occluded in the other image," Pg. 11, Lines 16-23); and
generating an output image based on the feature data and the modified plurality of offset pixels such that the input image and the output image form a stereo pair of images ("The two images are provided as the stereoscopic image pair for use in, for example, providing three-dimensional ("3D") content to a viewer," Pg. 3, Lines 10-11).
It is recognized that the citations and evidence provided above are derived from potentially different embodiments of a single reference. Nevertheless, it 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 to employ combinations and sub-combinations of these complementary embodiments, because Somanath et al. explicitly motivates doing so at least on page 58 lines 1-7 including “The implementations described herein may be implemented in, for example, a method or a process, an apparatus, a software program, a data stream, or a signal. Even if only discussed in the context of a single form of implementation (for example, discussed only as a method), the implementation of features discussed may also be implemented in other forms (for example, an apparatus or program). An apparatus may be implemented in, for example, appropriate hardware, software, and firmware.” and otherwise motivating experimentation and optimization.
The rejection of method claim 1 above applies mutatis mutandis to the corresponding limitations of computer readable media method claim 11 while noting that the rejection above cites to both device and method disclosures. Claim 11 is mapped below for clarity of the record and to specify any new limitations not included in claim 1.
Claim 3
Regarding claim 3, Somanath et al. teach the computer-implemented method of claim 2, further comprising:
receiving one or more user annotations for the input image, each user annotation comprising an identification of a selected portion of the input image and a ground truth disparity value associated with the selected portion ("Depth values are also modified manually in certain implementations. Modifications include, for example, deleting or replacing depth values. Manual modifications are made, in various implementations, within selected regions of the image," page 24, lines 18-21); and
aligning the pixel-wise predicted disparity values for the selected portion of the input image with the associated ground truth disparity values for the selected portion of the input image ("The operation of refining the depth map (760) is applied, in various implementations, to the corrected and sparse depth map from the previous stage, or the sparse-dense map of the hybrid approach," page 24, lines 26-28).
Claim 4
Regarding claim 4, Somanath et al. teach the computer-implemented method of claim 3, wherein each of the one or more user annotations for the input image comprises at least one of a bounding box encompassing a portion of the input image, one or more brush strokes denoting portions of the input image, or a manual selection of an object depicted in the input image ("Given the object boundary, which is provided by the mask or rotoscope, various implementations apply statistical or histogram filters within the segment, as determined by the object boundary, to remove noise. The refinement stage then fills the missing disparity values," page 24, lines 13-16).
Claim 5
Regarding claim 5, Somanath et al. teach the computer-implemented method of claim 1, wherein modifying each of the plurality of offset pixels comprises:
comparing the associated disparity map values for the plurality of offset pixels ("The process 1400 includes warping the particular image to a second view based on the disparity values, to produce a warped image from the second view (1430)," page 45, lines 25-26); and
rendering the one of the plurality of offset pixels as visible based on the one of the plurality of offset pixels having the highest disparity map value while hiding the pixels at the same pixel location that have lower disparity map values ("Additionally, if one of the disparity values (either dR or dL) is unavailable, then there is generally a high degree of confidence that there is an occlusion. A disparity value may be unavailable because, for example, the disparity value cannot be determined. The occlusion generally 20 relates to one of the two images. For example, the portion of the scene shown by the pixel associated with the disparity having the smaller magnitude, or shown by the pixel corresponding to the unavailable disparity value, is generally considered to be occluded in the other image," Pg. 11, Lines 16-23).
Claim 6
Regarding claim 6, Somanath et al. teach the computer-implemented method of claim 1, wherein all of the functions and transformations performed by the one or more machine learning models are fully differentiable ("The process 1400 includes determining disparity values for multiple pixels of the particular image (1420). Various implementations determine the disparity values 20 using a processor-based algorithm. A processor-based algorithm includes any algorithm operating on, or suited to be operated on, a processor. Such algorithms include, for example, fully automated algorithms and will generally include semi-automated algorithms. Processor-based algorithms permit user input
to be received," page 45, lines 17-24).
Claim 7
Regarding claim 7, Somanath et al. teach the computer-implemented method of claim 1, further comprising:
generating a disocclusion mask representing pixel locations in the extracted feature data where portions of an image background are disoccluded after applying the offset to each offset pixel represented by the feature data ("The left view 510 is shown in a left image 540 that also reveals occluded areas 545 and 548. The occluded areas 545 and 548 are only 15 visible in the left view 510 and not in the right view 520. This is because (i) the area in the right view 520 that corresponds to the occluded area 545 is covered by the wide cylinder 532, and (ii) the area in right view 520 that corresponds to the occluded area 548 is covered by the narrow cylinder 536," page 10, lines 13-18);
filling in the pixel locations represented by the disocclusion mask with image data selected from the image background ("a mask may also include other information, such as, for example, layer information if there are multiple foreground layers and/or background layers. Additionally, masks may provide the information in various formats, including, for example, bit flags and/or integer values," page 56, lines 23-26); and
generating the output image based on the modified plurality of offset pixels and the filled-in pixel locations represented by the disocclusion mask ("The two images are provided as the stereoscopic image pair for use in, for example, providing three-dimensional ("3D") content to a viewer," Pg. 3, Lines 10-11).
Claim 8
Regarding claim 8, Somanath et al. teach the computer-implemented method of claim 7, wherein the image data used to fill in pixel locations represented by the disocclusion mask is selected by applying a neighborhood-based self-attention technique ("The superpixels provide a quasi-uniform sampling, while keeping in mind image edges. That is, an image edge will typically not occur inside a super-pixel. The center of the superpixels is used in certain implementations to obtain a sparse depth map from triangulation. Accordingly, the disparity (and depth) is calculated with respect to, for example, the center pixel location I the superpixels," page 21, lines 22-26).
Claim 11
Regarding claim 11, Somanath et al. teach one or more non-transitory computer-readable media storing instructions that, when executed by one or more processors ("a storage medium accessible to or integrated with a computer system where the pipeline 620 is 30 implemented," Pg. 12, Lines 28-30), cause the one or more processors to perform the steps of:
generating, using one or more machine learning models, a predicted disparity map for an input image based on one or more depth values associated with pixels within the input image ("using the depth map to obtain a disparity map, and then using the disparity map to form the stereo image for the reference image," Pg. 26, Lines 6-8 and "divide the image into a fixed number of "super-pixels" page 21, lines 14-15, where super-pixels teach machine learning models);
extracting feature data from the input image, wherein the feature data represents the pixels within the input image ("matching (for example, flow or feature-based) is performed for all pixels," Pg. 21, Line 3)as a multi-resolution feature vector in a feature space ("The features can be tracked using any tracking scheme, or comparing the feature vectors (descriptors) using either the L 1 or the L2 norm. The various detectors and descriptors vary in terms of invariance to image transformations (such as scale change), type of image features selected, and dimension of the descriptor. One or more implementations use any of a variety of these known techniques," Pg. 19, lines 2-7);
applying, in the feature space ("As is known, given the dense depth map and the reference image, the corresponding stereo pair can be formed by using the depth map to obtain a disparity map, and then using the disparity map to form the stereo image for the reference image," Pg. 26, lines 5-8, where a dense depth map is a feature space), an offset to each pixel represented by the feature data based on per-pixel displacement vectors included in the predicted disparity map ("disparity map indicates the parallax/ horizontal shift for one or more pixels, and a dense disparity map typically indicates the parallax / horizontal shift for each pixel of the reference image," Pg. 26, Lines 6-10, where a disparity map is a feature space);
identifying a plurality of offset pixels represented by the feature data that are offset to a same pixel location ("left view 325 of the object is at the same horizontal position as the right view 327 of the object on the screen 320," Pg. 8, Lines 1-2);
assigning, based on the predicted disparity map, a visibility value to each of the plurality of offset pixels ("However, if d R is not substantially the same as -di_, then there may be an occlusion. For example, if the two disparity values are substantially different, after accounting for the sign, then there is generally a high degree of confidence that there is an occlusion," Pg. 11, Lines 12-15, where occlusion is a visibility value);
modifying, based on the visibility values, each of the plurality of offset pixels such that one of the plurality of offset pixels is visible and the others of the plurality of offset pixels are hidden ("Additionally, if one of the disparity values (either dR or dL) is unavailable, then there is generally a high degree of confidence that there is an occlusion. A disparity value may be unavailable because, for example, the disparity value cannot be determined. The occlusion generally 20 relates to one of the two images. For example, the portion of the scene shown by the pixel associated with the disparity having the smaller magnitude, or shown by the pixel corresponding to the unavailable disparity value, is generally considered to be occluded in the other image," Pg. 11, Lines 16-23); and
generating an output image based on the feature data and the modified plurality of offset pixels such that the input image and the output image form a stereo pair of images ("The two images are provided as the stereoscopic image pair for use in, for example, providing three-dimensional ("3D") content to a viewer," Pg. 3, Lines 10-11).
Claim 13
Regarding claim 13, Somanath et al. teach the one or more non-transitory computer-readable media of claim 12 wherein the instructions further cause the one or more processors to perform the steps of:
receiving one or more user annotations for the input image, each user annotation comprising an identification of a selected portion of the input image and a ground truth disparity value associated with the selected portion ("Depth values are also modified manually in certain implementations. Modifications include, for example, deleting or replacing depth values. Manual modifications are made, in various implementations, within selected regions of the image," page 24, lines 18-21); and
aligning the pixel-wise predicted disparity values for the selected portions of the input image with the associated ground truth disparity values for the selected portions of the input image ("The operation of refining the depth map (760) is applied, in various implementations, to the corrected and sparse depth map from the previous stage, or the sparse-dense map of the hybrid approach," page 24, lines 26-28).
Claim 14
Regarding claim 14, Somanath et al. teach the one or more non-transitory computer-readable media of claim 11, wherein the instructions to perform the steps of modifying each of the plurality of offset pixels further cause the one or more processors to perform the steps of:
comparing the associated disparity map values for the plurality of offset pixels ("The process 1400 includes warping the particular image to a second view based on the disparity values, to produce a warped image from the second view (1430)," page 45, lines 25-26); and
rendering the one of the plurality of offset pixels as visible based on the one of the plurality of offset pixels having the highest disparity map value while hiding the pixels at the same pixel location that have lower disparity map values ("Additionally, if one of the disparity values (either dR or dL) is unavailable, then there is generally a high degree of confidence that there is an occlusion. A disparity value may be unavailable because, for example, the disparity value cannot be determined. The occlusion generally 20 relates to one of the two images. For example, the portion of the scene shown by the pixel associated with the disparity having the smaller magnitude, or shown by the pixel corresponding to the unavailable disparity value, is generally considered to be occluded in the other image," Pg. 11, Lines 16-23).
2nd Claim Rejections - 35 USC § 103
Claims 2 and 12 are rejected under 35 U.S.C. 103 as obvious over International Patent Publication WO 2013 109252 A1, (Somanath et al.) in view of US Patent Publication 2021 0337175 A1, (Zhou et al.).
Claim 2
Regarding Claim 2, Somanath et al. teach the computer-implemented method of claim 1, wherein generating the predicted disparity map comprises:
assigning pixel-wise depth values to pixels representing foreground and background objects depicted in the reduced-resolution version of the input image ("scene which has fewer depth layers (for example, a scene that has far background and a simple object in the foreground)," page 22, lines 19-20); and
assigning pixel-wise predicted disparity values in the disparity map based on the depth values such that pixels in the predicted disparity map representing foreground objects are assigned greater disparity values than pixels representing background objects ("At the border of the person and the background, assume that the window contains, for example, part of the person's hand and part of part of the background. An in-between depth layer, generated using the mean, would generally result in the appearance that the hand was connected to the far background. This will typically look awkward to a viewer of the scene. A mode or median, in contrast, would generally result in part of the background appearing to stick to the hand. Note that this is avoided, in various implementations, by using super-pixels that respect image edges and, hopefully, do not create a segment that contains parts of both the person and background," page 23 lines 20-30).
Somanath et al. do not explicitly teach all of generating a reduced-resolution version.
PNG
media_image2.png
287
565
media_image2.png
Greyscale
However, Zhou et al. teach generating a reduced-resolution version of the input image ("the at least two second images may be acquired by downsampling the at least two first images, respectively," paragraph [0044]); and
upsampling the pixel-wise disparity map values associated with the reduced-resolution version of the input image to an original resolution of the input image ("Combine the depth map generated from the high-resolution images and the depth map generated from the low-resolution images," paragraph [0071] where combining teaches upsampling map values).
It would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify “Generating an image for another view” as taught by Somanath et al. to use “Image Processing Method and Device” as taught by Zhou et al.
The suggestion/motivation for doing so would have been that, “In the actual process of calculating a depth map, the depth map is usually calculated within a certain search region to reduce the calculation. However, for high-resolution images, this process causes nearby objects to be unrecognizable.” as noted by the Zhou et al. disclosure in paragraph [0005], which also motivates combination because the combination would predictably have a higher productivity as there is a reasonable expectation that more objects are recognized.
Claim 12
Regarding claim 12, Somanath et al. teach the one or more non-transitory computer-readable media of claim 11, wherein the instructions further cause the one or more processors to perform the steps of:
assigning pixel-wise depth values to pixels representing foreground and background objects depicted in the reduced-resolution version of the input image ("scene which has fewer depth layers (for example, a scene that has far background and a simple object in the foreground)," page 22, lines 19-20);
assigning pixel-wise predicted disparity values in the disparity map based on the depth values such that pixels in the predicted disparity map representing foreground objects are assigned greater disparity values than pixels representing background objects ("At the border of the person and the background, assume that the window contains, for example, part of the person's hand and part of part of the background. An in-between depth layer, generated using the mean, would generally result in the appearance that the hand was connected to the far background. This will typically look awkward to a viewer of the scene. A mode or median, in contrast, would generally result in part of the background appearing to stick to the hand. Note that this is avoided, in various implementations, by using super-pixels that respect image edges and, hopefully, do not create a segment that contains parts of both the person and background," page 23 lines 20-30); and
Somanath et al. do not explicitly teach all of generating a reduced-resolution version of the input image.
However, Zhou et al. teach generating a reduced-resolution version of the input image ("the at least two second images may be acquired by downsampling the at least two first images, respectively," paragraph [0044]); and
upsampling the pixel-wise disparity map values associated with the reduced-resolution version of the input image to an original resolution of the input image ("Combine the depth map generated from the high-resolution images and the depth map generated from the low-resolution images," paragraph [0071] where combining teaches upsampling map values).
Allowable Subject Matter
Claims 9-10 and 15-16 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.
Reference Cited
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
US Patent Publication 2022 02300343 A1 to Ye et al. discloses stereo matching method includes: obtaining a first binocular image; inputting the first binocular image into an object model for a first operation to obtain a first initial disparity map and a first offset disparity map with respect to the first initial disparity map; and performing aggregation on the first initial disparity map and the first offset disparity map to obtain a first target disparity map of the first binocular image.
US Patent Publication 2018 0255283 A1 to Li et al. discloses processing circuitry configured to: derive a disparity map of an object based on at least two images among multi-view images of the object; estimate confidences of disparity values in the disparity map using a classifier trained in advance; and perform an optimization process on the disparity map based on disparity values of reference pixels having confidences higher than a predetermined level.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HEATH E WELLS whose telephone number is (703)756-4696. 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, Ms. Jennifer Mehmood can be reached on 571-272-2976. 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.
/H.E.W/Examiner, Art Unit 2664
Date: 27 May 2026
/JENNIFER MEHMOOD/ Supervisory Patent Examiner, Art Unit 2664
Prosecution Insights