DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Lablans (US 2025/0386099 A1).
With respect to Claim 1, Lablans’099 shows a method, performed by at least one processor (Figure 8 2707 described in paragraph [0052] to include a processor. The function of the processor described in paragraph [0026].) of an electronic device (Figure 8 described in paragraph [0052] as an e-gimbal system comprising two image sensors 2700+2701), the method comprising:
obtaining a plurality of images using an image sensor (figure 3 and paragraph [0137] and figure 8 image sensor 2700) of the electronic device (e-gimbal system);
obtaining synthetic training data (Paragraph [0056] describes training data for neural network application.) for pre-training (paragraph [0135]) a burst processing network (The current application’s originally published specification paragraph [0025] describes bursts in regards to demosaicing method of multiple frames reconstructed together to form a single image. Prior art Lablans discloses in paragraphs [0055] and [0059] demosaicing for reconstructing a single image (panoramic) via a plurality of individual frames 2602-2608 (burst).);
performing implicit interpolation on the obtained plurality of images based on the pre-trained burst processing network (paragraph [0059] Demosaicing may include interpolation that smooths away some imperfections);
combining the plurality of images into a target image based on the implicit interpolation (paragraphs [0030], [0059], [0063], and [0076] describes image data to be demosaiced by interpolation in combining separate images into a panoramic video of high quality); and
outputting the target image to a display of the electronic device (paragraph [0196]).
With respect to Claim 2, Lablans’099 shows the method of claim 1, wherein the performing implicit interpolation comprises passing a non-integer coordinate to obtain a color (Paragraph [0030] describes demosacing for forming a single color pixel with the additional steps of interpolation. Paragraph [0209] describes interpolation may be simple methods such as scanline jumps such as moving 1 pixel for every 5 pixels horizontally (an example of non-integer coordinates.).
With respect to Claim 3, Lablans’099 shows the method of claim 1, wherein the performing implicit interpolation comprises, for each of the plurality of images, decoding image values for each two-dimensional coordinate (Paragraph [0085] describes using a decoder for scanline instructions. Paragraph [0209] describes interpolation may be simple methods such as scanline jumps such as moving 1 pixel for every 5 pixels horizontally (an example of non-integer coordinates.).
With respect to Claim 4, Lablans’099 shows the method of claim 1, wherein the obtaining the plurality of images comprises obtaining the plurality of images using a plurality of cameras (Figure 3 and paragraph [0137]).
With respect to Claim 5, Lablans’099 shows the method of claim 1, wherein the obtaining the plurality of images comprises capturing the plurality of images using a single camera (Without definition a single camera can comprise multiple lenses. Figure 8 depicts a plurality of image sensors 2700+2701 wherein each image sensor obtains an image. The image sensors are housed within a single housing which may be interpreted as a single camera.).
With respect to Claim 6, Lablans’099 shows the method of claim 1, wherein the performing implicit interpolation comprises fine tuning the burst processing network using self-supervised loss computation (paragraphs [0135] and [0188]).
With respect to Claim 7, Lablans’099 shows the method of claim 1, wherein the performing implicit interpolation comprises fine tuning the burst processing network using supervised loss computation (paragraphs [0074], [0089], and [0188]).
With respect to Claims 8 and 15, rejection analogous to those presented for claim 1, are applicable.
With respect to Claims 9 and 16, rejection analogous to those presented for claim 2, are applicable.
With respect to Claims 10 and 17, rejection analogous to those presented for claim 3, are applicable.
With respect to Claims 11 and 18, rejection analogous to those presented for claim 4, are applicable.
With respect to Claims 12 and 19, rejection analogous to those presented for claim 5, are applicable.
With respect to Claims 13 and 20, rejection analogous to those presented for claim 6, are applicable.
With respect to Claim 14, rejection analogous to those presented for claim 7, are applicable.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Dudhane et al. (US 2024/0135496 A1): paragraph [0101] Overall, the burst image processing network 600 contains 6.67M parameters. A separate model is trained for burst SR, burst low-light image enhancement and burst denoising using L.sub.1 loss only. While for SR on real data, the burst image processing network 600 is trained with pre-trained weights on SyntheticBurst dataset using aligned L.sub.1 loss. See Bhat et al., CVPR, 2021. The models are trained with Adam optimizer. Cosine annealing strategy is employed to steadily decrease the learning rate from 10.sup.−4 to 10.sup.−6 during training. See Ilya Loshchilov and Frank Hutter. Sgdr: Stochastic gradient descent with warm restarts. arXiv: 1608.03983, 2016, incorporated herein by reference in its entirety. Horizontal and vertical flips are used for data augmentation.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to IRIANA CRUZ whose telephone number is (571)270-3246. The examiner can normally be reached 10-6.
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, Akwasi M. Sarpong can be reached at (571) 270-3438. 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.
/IRIANA CRUZ/Primary Examiner, Art Unit 2681