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 .
Examiner Notes
Pre-grant publication [0007]-[0009] states that the present solution improves the situation of the “Lucas-Kanade reloaded” paper, and that one of the disadvantages of that approach is that “it does not take into account the heterogeneity of the raw images.” [0008]. However, the present claims do not require this heterogeneity.
On September 14, 2026, as a follow-up to the August 7, 2026 interview, representative David Brush left the examiner a voicemail declining to discuss a potential examiner amendment and instead requesting an office action.
Information Disclosure Statement
The Mairal powerpoint in the January 15, 2025 Information Disclosure Statement could not be considered because it lacks a date. 37 C.F.R. 19.8(b)(5). Other documents, such as Lecouat ICCV paper lakc date information, but the examiner was able to determine a date by finding the date of the ICCV 2021 conference. However, the Mairal powerpoint is by the inventors, and looks very relevant, but is missing the critical information as to whether or not it is available as prior art, and thus was not able to be considered.
The French and International Search Reports include a struck through portion of the claim showing what the Lucas Kanade Reloaded reference lacks, however, this struck through portion is not in English, and thus was not considered.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-15 (all claims) are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites various “units” and “modules.” At the outset, it is unclear what difference, if any, is intended (e.g., individually, each is considered a nonce word for a 112(f) interpretation, but it is unclear how to interpret two different nonce words in the same claim). Further, the structural meaning of these terms is unclear. For example, the initialisation module includes both a computer (suggesting that the module is hardware), but also a convolutional neural network. Given the juxtaposition with the computer, this sounds as though the convolutional neural network is intended to be claimed as software per se, though it may also be that the CNN is executed by the computer.
Claims 1, 12, and 15 recite “a plurality of pairs each formed by an image,” but the grammar is incorrect (e.g., it is unclear how a single image provides the two items needed for a pair). Note that other parts of these claims refer to “the images” (plural), but the antecedent basis is unclear because the literal language of the claim introduces the image in the singular.
Claim 1 recites an “estimator,” but this is new terminology. MPEP 2173.05(a). One option to overcome this rejection is to recite the steps as computer instructions or circuitry.
Claims 1, 12, and 15 recite both an “auxiliary variable” and a “estimation variable,” but these are new terminology. MPEP 2173.05(a). One option to overcome this rejection is to include wherein clauses that explain/define these variables.
Dependent claims are likewise rejected.
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.
Claims 1-6 and 8-15 (all but claim 7) are rejected under 35 U.S.C. 103 as being unpatentable over Lecouat B, Ponce J, Mairal J. Aliasing is your ally: End-to-end super-resolution from raw image bursts. ArXiv, abs/2104.06191. 2021;7. (“Version 1”) in view of Tursun OT, Akyüz AO, Erdem A, Erdem E. An objective deghosting quality metric for HDR images. InComputer Graphics Forum 2016 May (Vol. 35, No. 2, pp. 139-152). (“Tursun”).
A mapping to a reproduction of the claims is not provided because the February 17, 2025 amendment fails to comply with 37 C.F.R. 1.52(a)(1)(v): “Presented in a form having sufficient clarity and contrast between the paper and the writing thereon to permit the direct reproduction of readily legible copies in any number by use of … optical character recognition.” Going forward, Applicant may wish to submit a .docx format version of the claims.
However, the specification admits that Applicant understands the distinctions between the “Lucas-Kanade reloaded” paper and the present claims. See pre-grant publication [0007]-[0008] (the pre-grant publication is cited because the specification lacks paragraph numbers). Further, the examiner finds that since the cited Version 1 paper is written by the inventors and describes the present technology using the same terms that one of ordinary skill in the art would understand the thrust of the rejection.
Further, as per the interview of August 7, 2026, the primary reference in this rejection is Version 1 of the “Lucas-Kanade reloaded” paper. See https://arxiv.org/abs/2104.06191
PNG
media_image1.png
497
1875
media_image1.png
Greyscale
PNG
media_image2.png
95
297
media_image2.png
Greyscale
As per the above inset submission history, the inventor Bruno Lecouat describes the primary reference as version 1 of the “Lucas-Kanade reloaded” paper.
The specification alleges the below shortcomings of the primary reference (pre-grant publication [0008]).
However, Tursun teaches:
“it does not take into account the heterogeneity of the raw images, i.e. their respective exposure times, and nor does it provide deghosting” (Tursun, section 3, “We studied the outputs of several deghosting algorithms for a variety of exposure sequences”)
“the optimisation proposed to minimise an energy function and solve an inverse problem is computationally intensive and time-consuming.”
Pre-grant publication [0181] explains that the distinction between Lecouat and the present invention is that the present invention avoids steps. However, none of the claim limitations are negative, meaning that the optimization of version 1 (as modified by Tursun, below) reads on the claimed optimization module.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Tursun to the teachings of Version 1 such that Tursun’s deghosting is used with Version 1’s images for the purpose of improved reconstruction (Tursun, abstract) and because Version 1 says that this is a focus of future work. See, Version 1, Fig. A8, caption and image in the bottom right corner (showing ghosting).
Based on the above, this is an example of “combining prior art elements according to known methods to yield predictable results.” MPEP 2143.
For claim 2, the Version 1 paper teaches the claimed CNN for different spatial resolutions (Version 1 paper, section 2, last paragraph, “Learning super-resolution models from real LR/HR image pairs is quite challenging since it requires in general using separate cameras with different lenses and spatial resolution, with inevitable spatial and spectral misalignments. As shown by our experiments, our method, although trained from synthetic LR images, gives excellent results with real bursts taken from different smartphones and cameras.”)
Tursun teaches the claimed distortion parameter. (Tursun, Fig. 1)
For claim 3, (Tursun, section 4.3, last paragraph, “we compute an image pyramid of 5 levels by Gaussian smoothing and downsampling.”)
For claim 4, (Version 1 paper, section 3.2, equation (4). Version 1 teaches “where z is an auxiliary variable”)
Claim 5 is taught by version 1, Fig. 2:
PNG
media_image3.png
57
318
media_image3.png
Greyscale
For claim 6, Tursun, section 4.1.1, equation (4) teaches the claimed normalizing weights relative to the sum of the other weights. As shown in Tursun, section 4.1.1, equations (2) and (3), the (p) values that are used in Equation (4) are based on the exposures (see the top paragraph of p. 142, left side). The claimed confidence value (g sub p) is a result of combining Lecouat’s CNN output with Tursun’s weights. See, e.g., the Max likelihood steps in Lecouat, Fig. 2. Tursun, section 4 states “The outputs are the distortion maps,” and this teaches the claimed distortion operator. Additionally, pre-grant publication [0181] admits that the Lecouat paper teaches “the distortion parameters pk.”
Claim 8 is rejected as per claim 2. See, in particular, Version 1, fig. 5.
For claim 9, see the mapping of claim 4. Additionally, Tursun, section 5.5, first paragraph, teaches the claimed binary mask and deghosting weights.
For claim 10, (Version 1, section 4, “Training procedure and data,” “we perform 80 000 iterations of the ADAM Optimizer.”)
For claim 11, (Version 1, Fig. 5 caption, “ResUNet architecture.”)
Claim 12 is rejected as per claim 1.
Claim 13 is rejected as per claim 6.
Claim 14 is taught by Tursun, section 4.2, equation 8. Note that Tursun, section 4.1 explains that the irradiance is based on the different exposures and that these values are summed. Additionally, claim 14 only requires “making it possible to parameterise,” not actually performing the computation.
Claim 15 is rejected as per claim 1.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Lecouat B, Ponce J, Mairal J. Aliasing is your ally: End-to-end super-resolution from raw image bursts. ArXiv, abs/2104.06191. 2021;7. (“Version 1”) in view of Tursun OT, Akyüz AO, Erdem A, Erdem E. An objective deghosting quality metric for HDR images. InComputer Graphics Forum 2016 May (Vol. 35, No. 2, pp. 139-152). (“Tursun”) and “Bilinear Interpolation,” Wikipedia, July 15, 2021, retrieved from https://en.wikipedia.org/w/index.php?title=Bilinear_interpolation&oldid=1033800184 (“Wikipedia”).
The combination of Version 1 and Tursun (see the mapping of claim 1) teaches the alignment of claim 7 (Version 1, Fig. 4), but not the use of bilinear interpolation.
However, Wikipedia teaches bilinear interpolation. See, e.g., the section titled “Application in image processing.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Wikipedia to the teachings of the combination of Version 1 and Tursun such that Wikipedia’s bilateral interpolation is used on the images of the combination of Version 1 and Tursun for the purpose of performing basic resampling (Wikipedia, intro) or because Version 1 and Tursun use of different types of images are a situation where “perfect image transformation with pixel matching is impossible.” Wikipedia, section “Application in image processing.”
Based on the above, this is an example of “combining prior art elements according to known methods to yield predictable results.” MPEP 2143.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 9153027 B2 – Fig. 5A, particularly module 510
US 20220014684 A1 – Fig. 10, particularly step 506
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DAVID ORANGE whose telephone number is (571)270-1799. The examiner can normally be reached Mon-Fri, 9-5.
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, Gregory Morse can be reached at 571-272-3838. 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.
/DAVID ORANGE/Primary Examiner, Art Unit 2663
Prosecution Insights