DETAILED ACTION
1. This Office Action for U.S. Patent Application No. 17/949,153 is responsive to communications filed on 05/25/2025, in reply to the Request for continued examination received on 10/13/2025. Currently, claims 1-20 are pending.
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
3. The information disclosure statement (IDS) submitted on 10/13/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Continued Examination Under 37 CFR 1.114
4. A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 10/13/2025 has been entered.
Claim Rejections - 35 USC § 103
5. 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.
6. Claim(s) 1-2, 4-5, 8-11, 15, 17 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Liu et al., [US Pub. No.: 2020/0394752 A1] hereinafter Liu1 in view of Chi et al., [US Pub. No.: 2021/0279840 A1].
Re. Claim 1, Liu1 discloses:
One or more processors, [processor circuitry 1202, which may be one or more processing elements/devices configured to perform basic arithmetical, logical, and input/output operations by carrying out instructions |Fig. 12, 0044]
In the same field of endeavor Chi discloses:
comprising: circuitry to use one or more neural networks [neural networks which perform all or part of a video frame interpolation |0053] to blend two or more intermediate video frames generated from a first video frame and a second video frame to generate a blended intermediate video frame between the first video frame and the second video frame [In the proposed single CNN, at each level, in addition to the optical flow, a blending mask b.sub.ti is also generated. Therefore, the intermediate frames can be generated (e.g. synthesized) as| Fig. 12, 13, 0112, 0124].
Therefore it would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention to combine Liu1 with Chi to generate all new intermediate frames in one processing pass with high temporal consistency [0025].
Re. Claim 2, Liu1 discloses:
The one or more processors of claim 1, wherein the two or more intermediate video frames between the first video frame and the second video frame are to be blended based, at least in part, on one or more blending factors [two video frames are blended using interpolation algorithms that typically estimate optical flow or its variations to produce interpolation results. |0018-0020].
Re. Claim 4, Liu1 discloses:
The one or more processors of claim 1, wherein the one or more neural networks are to blend the two or more intermediate video frames based, at least in part, on one or more optical flow vectors between the first video frame and the second video frame [the CAS 200 includes content extractors 205, optical flow estimators (OFEs) 210, spatial warping engines (SWEs)for blending/warping frames |Fig.2 el 210, 0027].
Re. Claim 5, Liu1 discloses:
The one or more processors of claim 1, wherein the one or more neural networks are to blend the two or more intermediate video frames based, at least in part, on one or more motion types [Optical flow estimation uses precise per-pixel localization and finds correspondences between two input images, …also learning to match them at different locations in the two images… an optical flow describes how pixels move between images, which may include a data structure that indicates pixel correspondences between two images (or video frames).|0029].
Re. Claim 8, This claim is interpreted and rejected for the same reason set forth in claim 1.
Re. Claim 9, Liu1 discloses:
The computer-implemented method of claim 8, further comprising: generating one or more additional frames [a frame synthesis deep neural network that directly produces an intermediate frame from the pre-warped frames to further improve the interpolation quality wherein the pre warped image is interpreted as being equivalent to the additional image |0021];
and blending the blended intermediate video frame with the one or more additional frames [to improve interpolation the pre-3warped frames and the intermediate frames are blended |0021].
Re. Claim 10, Liu1 discloses:
The computer-implemented method of claim 8, wherein using the one or more neural networks to generate the blended intermediate video frame is based [The CAS architecture 200 (or simply “CAS 200”) is context-aware synthesis neural network that warps not only the input frames but also their pixel-wise contextual information and uses them to interpolate a high-quality intermediate frame. |0027], at least in part, on a first camera position of the first video frame and a second camera position of the second video frame [use convolutional neural networks for video frame interpolation either had to retrain their synthesis network for a specific t or continue the interpolation recursively in order to achieve similar results [R31, R32]. Furthermore, the embodiments are not limited to video frame interpolation. In fact, various embodiments can also be utilized to synthesize between stereo frames |Fig.9 0062].
Re. Claim 11, Liu1 discloses:
The computer-implemented method of claim 8, wherein using the one or more neural networks to blend the two or more intermediate video frames between the first video frame and the second video frame is based, at least in part, on optical flow between the first video frame and the second video frame [the CAS 200 includes content extractors 205, optical flow estimators (OFEs) 210, spatial warping engines (SWEs)for blending/warping frames |Fig.2 el 210, 0027].
Re. Claim 15, This claim is interpreted and rejected for the same reason set forth in claim 1 and 8, including a computer system [fig.12 el 1200].
Re. Claim 17, This claim is interpreted and rejected for the same reason set forth in claim 10.
Re. Claim 20, This claim is interpreted and rejected for the same reason set forth in claim 14.
7. Claim(s) 3, 6, and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lui1 in view Chi in further view of Hu [US Pub. No.: 2020/0267348].
Re. Claim 3, The combination Liu1 in view Chi, specifically Liu1 discloses:
The processor of claim 1, wherein the one or more neural networks are to blend the two or more intermediate video frames based, at least in part [two consecutive frames are interpolated… using neural network to generate an intermediate frame using blending factors |0003, 0019, 0027, 0054],
In the same field of endeavor Hu discloses:
on one or more motion vectors of objects in at least one of the first video frame and the second video frame [The motion vector calculation circuit calculates an object motion vector representing the movement of the object between the first frame and the second frame based on the first-frame and the second-frame object positions|0012, 0051-0052].
Therefore, it would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention to combine Liu1 with Chi to generate all new intermediate frames in one processing pass with high temporal consistency [0025] and the context-aware synthesis for video frame interpolation of Liu1 with the motion estimation Hu to detect object movement between consecutive frames.
Re. Claim 6, The combination Liu1 in view Chi, specifically Liu1 discloses:
The one or more processors of claim 1, wherein the one or more neural networks are to blend the two or more intermediate video frames based, at least in part [two video frames are blended using interpolation algorithms that typically estimate optical flow or its variations to produce interpolation results. |0018-0020],
In the same field of endeavor Hu discloses:
on one or more first motion vectors indicating motion from the first video frame and the second video frame [The motion vector selection circuit generates a plurality of candidate motion vectors based on the plurality of spatial motion vectors and the plurality of temporal motion vectors. |0012-0013, 0051-0052], the one or more first motion vectors based, at least in part, on one or more second motion vectors indicating motion from the second video frame to the first video frame [The motion vector calculation circuit calculates an object motion vector representing the movement of the object between the first frame and the second frame based on the first-frame and the second-frame object positions|0012, 0051-0052].
Therefore, it would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention to combine Liu1 with Chi to generate all new intermediate frames in one processing pass with high temporal consistency [0025] and the context-aware synthesis for video frame interpolation of Liu1 with the motion estimation Hu to detect object movement between consecutive frames.
Re. Claim 12, The combination Liu1 in view Chi, specifically Liu1 discloses:
and generating the intermediate video frame based, at least in part, on blending the first motion vectors and the second motion vectors [two consecutive frames are interpolated… using neural network to generate an intermediate frame using blinding factors |0003, 0019, 0027, 0054].
In the same field of endeavor Hu discloses:
The computer-implemented method of claim 8, further comprising: receiving one or more first motion vectors from the first video frame to the second video frame [The motion vector selection circuit generates a plurality of candidate motion vectors based on the plurality of spatial motion vectors and the plurality of temporal motion vectors. |0012-0013, 0051-0052];
generating one or more second motion vectors from the second video frame to the first video frame based, at least in part, on the first motion vectors [The motion vector calculation circuit calculates an object motion vector representing the movement of the object between the first frame and the second frame based on the first-frame and the second-frame object positions|0012, 0051-0052];
Therefore, it would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention to combine Liu1 with Chi to generate all new intermediate frames in one processing pass with high temporal consistency [0025] and the context-aware synthesis for video frame interpolation of Liu1 with the motion estimation Hu to detect object movement between consecutive frames.
Re. Claim 16, The combination Liu1 in view Chi, specifically Liu1 discloses:
The computer system of claim 15, wherein the one or more neural networks are to blend the two or more intermediate video frames based, at least in part [two video frames are blended using interpolation algorithms that typically estimate optical flow or its variations to produce interpolation results. |0018-0020],
In the same field of endeavor Hu discloses:
on one or more motions of dynamic objects displayed in at least one of the first video frame and the second video frame [a moving object 10 in the source frames OF1˜OF5 and the interpolated frames MF1˜MF4 is shown. In the context, movement of the object 10 can be represented as an object motion vector MVobj.|Figs. 1A and B, 0007].
Therefore, it would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention to combine Liu1 with Chi to generate all new intermediate frames in one processing pass with high temporal consistency [0025] and the context-aware synthesis for video frame interpolation of Liu1 with the motion estimation Hu to detect object movement between consecutive frames.
Re. Claim 19, The combination Liu1 in view Chi does not disclose:
The computer system of claim 15, wherein the blended intermediate video frame corresponds to a time that is between a time of the first video frame and a time of the second video frame.
In the same field of endeavor Hu discloses:
The computer system of claim 15, wherein the blended intermediate video frame corresponds to a time that is between a time of the first video frame and a time of the second video frame [The first-frame candidate circuit locates a first first-frame candidate position and a second first-frame candidate position in a first frame based on a first-frame similarity measure distribution at a current time.|0012,0046].
Therefore, it would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention to combine Liu1 with Chi to generate all new intermediate frames in one processing pass with high temporal consistency [0025] and the context-aware synthesis for video frame interpolation of Liu1 with the motion estimation Hu to detect object movement between consecutive frames.
8. Claim(s) 7 and 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Liu1 in view of Hu in further view of Liu2 et al., [US Pub. No.: 2020/0012940 A1].
Re. Claim 7, The combination of Liu1 with Chi and Hu does not distinctly disclose:
The processor of claim 1, wherein the one or more neural networks are to blend the two or more intermediate video frames based, at least in part, on depths of pixels in at least one of the first video frame and the second video frame.
In the same field of endeavor Liu2 discloses:
The processor of claim 1, wherein the one or more neural networks are to blend the two or more intermediate video frames based, at least in part, on depths of pixels in at least one of the first video frame and the second video frame [the input layer may hold pixels data of the input image frames 110. The three dimensions of the 3D input volume of the input layer may include height, width, and depth. The depth dimension of the input layer may be a color of one or more image frames 110 (e.g., Red, Green, Blue (RGB) channels for each frame). |0039, 0049].
Therefore, it would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention to combine the context-aware synthesis for video frame interpolation of Liu1 with the motion estimation Hu to detect object movement between consecutive frames. Furthermore, the frame interpolation via adaptive convolution of Liu2 to have raw pixel data of an image for holding pixel data of the input image frames 110 that include height, width, and depth of pixel data.
Re. Claim 14, This claim is interpreted and rejected for the same reason set forth in claim 7.
Allowable Subject Matter
9. Claims 13 and 18 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.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 6393162 B1
US 20170191243 A1
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HOWARD D BROWN JR whose telephone number is (571)272-4371. The examiner can normally be reached Monday - Friday 7:30AM - 5:00PM EST.
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, Sathyanarayanan Perungavoor can be reached at 5712727455. 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.
HOWARD D. BROWN JR
Primary Examiner
Art Unit 2488
/HOWARD D BROWN JR/Examiner, Art Unit 2488
Prosecution Insights