DETAIL OFFICE ACTIONS
The United States Patent & Trademark Office appreciates the response filed for the current application that is submitted on 3/26/2026. The United States Patent & Trademark Office reviewed the following documents submitted and has made the following comments below.
Amendment
Applicant submitted amendments on 3/26/2026. The Examiner acknowledges the amendment and has reviewed the claims accordingly.
Applicant Arguments:
In regards to Argument 1, Applicant/s state/s Smirnov2022A in view of Pottorff does not teach on the amended claims, therefore, the rejection of 35 U.S.C. 103 should be removed.
Examiner’s Responses:
Applicant’s arguments, see Remarks, filed 3/26/2026, with respect to the rejection(s) of claim(s) 1-4, 11-19 under 35 U.S.C. 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration and amendments to claim, a new ground(s) of rejection is made with Ferres et al (U.S. Patent Pub. No. 2020/0151854, hereafter referred to as Ferres) in view of Hu et al (U.S. Patent Pub. No. 2020/0265567, hereafter referred to as Hu).
Specifically, the Ferres teaches an image signal processing pipeline that captures and processes a sequence of image frames. Specifically, Ferres teaches recursively reducing temporal noise across a sequence of input images by combining a current image with noise feedback information from a previously processed reference frame, where the reference frame may be a local motion compensated frame, a global motion compensated frame, or a combination thereof (paragraph 114). Ferres further teaches a warp and blend unit that warps and blends images together to correct for distortions, applying transformations subject to a close to identity constraint, and processing image data in raster-in/raster-out order (paragraphs 119–120). Additionally, Ferres teaches a scaler that processes output images in patches or blocks of pixels, such as 16×16 or 8×8 blocks (paragraph 123). Thus, Ferres teaches a system that captures images in a sequence, determines motion regions through local and global motion compensation, and stages the removal of motion artifacts by combining frames at each processing stage. The Examiner finds Hu is related to Ferres for detecting motion and removing motion. Hu teaches a convolutional neural network (CNN)-based approach for multi-exposure fusion of multiple image frames. Specifically, Hu teaches using a CNN to generate blending maps associated with multiple image frames, where the blending maps contain or are based on both a measure of motion in the image frames and a measure of how well exposed different portions of the image frames are (paragraphs 4, 38). Hu further teaches generating a final image of the scene by blending the image frames using the blending maps, which reduces ghosting artifacts caused by moving objects in dynamic scenes and recovers image details lost due to over-exposure or under-exposure (paragraph 38). Hu also teaches determining whether to discard captured frames based on an amount of blur, identifying portions prone to blur, and performing deblurring only in the identified portions before applying filtering and motion compensation to generate a final image (paragraph 7). The reason to combine is as follows: It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the image combining method of Ferres by replacing the step of simply combining images with the CNN-based blending technique taught by Hu, resulting in a system that captures images in a sequence, determines motion regions across all images, stages the removal of motion artifacts through motion compensation, and blends the images at each stage of the process using intelligently generated blending maps. One of ordinary skill in the art would have been motivated to make this combination because Hu teaches that cameras on mobile electronic devices typically have poor performance in low-light situations, and while it is possible to increase the amount of light collected at an image sensor by increasing the exposure time, this also increases the risk of producing blurred images due to object and camera motion (paragraph 2, Hu). Incorporating Hu’s CNN-based blending maps into the sequential processing pipeline of Ferres would enable the system to intelligently account for both motion and exposure quality at each blending stage, thereby reducing ghosting artifacts and recovering image details that would otherwise be lost (paragraph 38, Hu).
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 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(a) which forms the basis for all obviousness rejections set forth in this Office action:
(a) A patent may not be obtained though the invention is not identically disclosed or described as set forth in section 102 of this title, if the differences between the subject matter sought to be patented and the prior art are such that the subject matter as a whole would have been obvious at the time the invention was made to a person having ordinary skill in the art to which said subject matter pertains. Patentability shall not be negatived by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103(a) 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.
Claims 1-4, 11-16, 19, 20 are rejected under 35 U.S.C. 103(a) as being unpatentable over Ferres et al (U.S. Patent Pub. No. 2020/0151854, hereafter referred to as Ferres) in view of Hu et al (U.S. Patent Pub. No. 2020/0265567, hereafter referred to as Hu).
Regarding Claim 1, Ferres teaches an image processing method, comprising:
a first motion compensated noise reduction (MCNR) stage (Figure 6 item 620, item 650, Ferres teaches using denoising of the images.), including blending a current frame with either a cached image or a long-term reference image to obtain a fused image (paragraph 119- paragraph 121, Ferres teaches blend unit that applies one or more transformation to the frames to correct distortions at image edges.),
wherein the cached image is loaded from a buffer unit and different than the long-term reference image (paragraph 68, paragraph 99, Ferres teaches using a reference video frame,) and the long-term reference image is derived from a static region of each input frame in a sequence of input frames (paragraph 113, paragraph 114, Ferres teaches temporal noise reduction unit using reduce noise of the current frame by taking the input image with the reference frame for compensated frame out by local motion.); and
a second MCNR stage (Figure 6 item 690, Ferres teaches reconstruction of the all the denoise images, which is interpreted to the second MCNR stage).
Ferres does not explicitly disclose the following including blending the fused image with the other of the cached image or the long-term reference image to obtain an output image.
Hu is in the same field of art of image processing and reviewing motion artifacts. Further, Hu teaches including blending the fused image with the other of the cached image or the long-term reference image to obtain an output image (paragraph 38, paragraph 39, paragraph 43, paragraph 58, Hu teaches different images that are fused together using a blending map to reduce blurring.).
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 Ferres, which performs combining images together with replacing the step of blending images instead just combining that is taught by Hu, to make the invention that captures images in a sequence and then determines the motion regions of all the images and starts to stage the remove of the motion or motion artifacts (Ferres) with blending the images at each stage of the process (Hu); thus, one of ordinary skilled in the art would be motivated to combine the references since as another example, cameras on mobile electronic devices typically have poor performance in low-light situations; while it is possible to increase the amount of light collected at an image sensor by increasing the exposure time, this also increases the risk of producing blurred images due to object and camera motion (paragraph 2, Hu).
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.
In regards to Claim 2, Ferres in view of Hu discloses an LTR- generation process for deriving the long-term reference image, wherein the LTR- generation process comprises:
estimating motion information of multiple input frames in the sequence of input frames (paragraph 38 Hu teaches measuring the motion of the image to determine the amount motion.); identifying the static region in each of the input frames based on the motion information (paragraph 58, paragraph 59, paragraph 62, paragraph 63, Hu teaches determining a motion regions and the examiner interprets that if motion regions are determine the other parts do not contain motion, knowing the regions to correct with motion.); and
blending the input frames based on their respective static regions to obtain the long-term reference image (Figure 24, item 2412, 2414, 2416, Hu teaches a blending and the images together to generate a final image scene and final image; Figure 6 item 695, Ferres teaches outputting the final image.).
In regards to Claim 3, Ferres in view of Hu discloses wherein the LTR-generation process further includes generating a confidence map that corresponds to the long-term reference image based on the motion information of the sequence of input frames (paragraph 121-paragraph 124, Ferres teaches a cost map for blending the images.); and wherein the first MCNR stage further includes determining a set of weights (paragraph 36, Hu teaches using a scalar-valued weight map for the blending the images together.) for blending each pixel of the current frame with a corresponding pixel of the long-term reference image based on the confidence map (paragraph 58, paragraph 59, paragraph 62, paragraph 63, Hu teaches the blended image.).
In regards to Claim 4, Ferres in view of Hu discloses wherein the first MCNR stage further includes blending the current frame with the long-term reference image to obtain the fused image (paragraph 62, paragraph 63, Hu teaches blending of the images to remove motion.); and
wherein the second MCNR stage further includes blending the fused image with the cached image to obtain the output image (Figure 6 item 690, Ferres teaches denoising and then a reconstruction method of the images to generate a final output image.); and
PNG
media_image1.png
497
665
media_image1.png
Greyscale
wherein the obtained output image is stored in the buffer unit as the cached image (paragraph 44, Hu teaches using the memory for storing the images.)
In regards to Claim 11, Ferres in view of Hu discloses wherein the first MCNR stage further includes blending the current frame with the cached image to obtain the fused image (paragraph 119, paragraph 128-paragraph 135, Ferres teaches multiple blending of the images for different stages. ); and
PNG
media_image1.png
497
665
media_image1.png
Greyscale
wherein the second MCNR stage further includes blending the fused image with the long-term reference image to obtain the output image (paragraph 119, paragraph 128-paragraph 135, Ferres teaches multiple blending of the images for different stages, see Figure 6 for the different stages); and
wherein either the obtained output image or the fused image is stored in the buffer unit as the cached image (paragraph 44, Hu teaches using the memory for storing the images.)
In regards to Claim 12, Ferres in view of Hu discloses wherein the first MCNR stage and the second MCNR stage are applied to an image pyramid architecture (paragraph 128, Figure 6, Ferres teaches different stages in the denoise of motion.)
PNG
media_image1.png
497
665
media_image1.png
Greyscale
Regarding Claim 13, Ferres teaches an image processing device, comprising:
a buffer unit, for storing a cached image (paragraph 120, Hu teaches a memory);
a first motion compensated noise reduction (MCNR) unit (Figure 6 item 620, item 650, Ferres teaches using denoising of the images.), configured to blend a current frame with either the cached image or a long-term reference image to obtain a fused image (paragraph 119- paragraph 121, Ferres teaches blend unit that applies one or more transformation to the frames to correct distortions at image edges.),
wherein the cached image is loaded from the buffer unit and different than the long-term reference image (paragraph 68, paragraph 99, Ferres teaches using a reference video frame,), and
the long-term reference image is derived from a static region of each input frame in a sequence of input frames (paragraph 113, paragraph 114, Ferres teaches temporal noise reduction unit using reduce noise of the current frame by taking the input image with the reference frame for compensated frame out by local motion.); and
a second MCNR unit (Figure 6 item 690, Ferres teaches reconstruction of the all the denoise images, which is interpreted to the second MCNR stage).
Ferres does not explicitly disclose configured to blend the fused image with the other of the cached image or the long-term reference image to obtain an output image.
Hu is in the same field of art of image processing and reviewing motion artifacts. Further, Hu teaches configured to blend the fused image with the other of the cached image or the long-term reference image to obtain an output image (paragraph 38, paragraph 39, paragraph 43, paragraph 58, Hu teaches different images that are fused together using a blending map to reduce blurring.).
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 Ferres, which performs combining images together with replacing the step of blending images instead just combining that is taught by Hu, to make the invention that captures images in a sequence and then determines the motion regions of all the images and starts to stage the remove of the motion or motion artifacts (Ferres) with blending the images at each stage of the process (Hu); thus, one of ordinary skilled in the art would be motivated to combine the references since as another example, cameras on mobile electronic devices typically have poor performance in low-light situations; while it is possible to increase the amount of light collected at an image sensor by increasing the exposure time, this also increases the risk of producing blurred images due to object and camera motion (paragraph 2, Hu).
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
In regards to Claim 14, Ferres in view of Hu discloses an LTR-generation unit, configured to estimate motion information of multiple input frames in the sequence of input frames (paragraph 38 Hu teaches measuring the motion of the image to determine the amount motion.), identify the static region in each of the input frames based on the motion information (paragraph 58, paragraph 59, paragraph 62, paragraph 63, Hu teaches determining a motion regions and the examiner interprets that if motion regions are determine the other parts do not contain motion, knowing the regions to correct with motion.), and blend the input frames based on their respective static regions to obtain the long-term reference image (Figure 24, item 2412, 2414, 2416, Hu teaches a blending and the images together to generate a final image scene and final image; Figure 6 item 695, Ferres teaches outputting the final image.).
In regards to Claim 15, Ferres in view of Hu discloses wherein the LTR-generation unit is further configured to generate a confidence map that corresponds to the long-term reference image based on the motion information of the sequence of input frames (paragraph 121-paragraph 124, Ferres teaches a cost map for blending the images.); wherein the first MCNR unit is further configured to determine a set of weights (paragraph 36, Hu teaches using a scalar-valued weight map for the blending the images together.) for blending each pixel of the current frame with a corresponding pixel of the long-term reference image based on the confidence map (paragraph 58, paragraph 59, paragraph 62, paragraph 63, Hu teaches the blended image.).
In regards to Claim 16, Ferres in view of Hu discloses wherein the first MCNR unit is further configured to blend the current frame with the long-term reference image to obtain the fused image (paragraph 62, paragraph 63, Hu teaches blending of the images to remove motion.); and wherein the second MCNR unit is further configured to blend the fused image with the cached image to obtain the output image (Figure 6 item 690, Ferres teaches denoising and then a reconstruction method of the images to generate a final output image.);
PNG
media_image1.png
497
665
media_image1.png
Greyscale
wherein the obtained output image is stored in the buffer unit as the cached image (paragraph 44, Hu teaches using the memory for storing the images.).
In regards to Claim 19, Ferres in view of Hu discloses wherein the first MCNR unit is further configured to blend the current frame with the cached image to obtain the fused image (paragraph 119, paragraph 128-paragraph 135, Ferres teaches multiple blending of the images for different stages. ); and
PNG
media_image1.png
497
665
media_image1.png
Greyscale
wherein the second MCNR unit is further configured to blend the fused image with the long-term reference image to obtain the output image (paragraph 119, paragraph 128-paragraph 135, Ferres teaches multiple blending of the images for different stages, see Figure 6 for the different stages); and
wherein either the obtained output image or the fused image is stored in the buffer unit as the cached image (paragraph 44, Hu teaches using the memory for storing the images.)
In regards to Claim 20, Ferres in view of Hu discloses wherein the first MCNR unit and the second MCNR unit are applied to an image pyramid architecture (paragraph 128, Figure 6, Ferres teaches different stages in the denoise of motion.)
PNG
media_image1.png
497
665
media_image1.png
Greyscale
Allowable Subject Matter
Claims 5-10, 17, and 18 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.
In regards to Claim 5 and 17, no prior arts teach the specific blending levels of the reference image as recited in the claim “including blending the level-1 current frame with the level-1 long-term reference image to obtain a level-1 fused image; a level-0 first MCNR stage, including deriving a level-0 fused image through blending the level-0 current frame with the level-0 long-term reference image and performing a reconstruction process based on the level-1 fused image; resizing the level-0 fused image; a level-1 second MCNR stage, including blending the resized level-0 fused image with a level-1 cached image to obtain a level-1 output image; and a level-0 second MCNR stage, including deriving a level-0 output image through blending the level-0 fused image with the level-0 cached image and performing the reconstruction process based on the level-1 output image; wherein said first MCNR stage is the level-0 first MCNR stage, said second MCNR stage is the level-0 second MCNR stage, said current frame is the level-0 current frame, said cached image is the level-0 cached image, said long-term reference image is the level-0 long-term reference image, said fused image is the level-0 fused image, and said output image is the level-0 output image.”
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 ONEAL R MISTRY whose telephone number is (313)446-4912. The examiner can normally be reached 9am-5pm.
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.
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.
/ONEAL R MISTRY/Supervisory Patent Examiner, Art Unit 2674
Prosecution Insights