DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
2. This is in response to the applicant response filed on 09/30/2026. The terminal disclaimer received on 09/30/2026 has been approved. In the applicant’s response, claims 1-2, 11-12, and 20 were amended. Accordingly, claims 1-20 are pending and being examined. Claims 1, 11, and 20are independent form.
Non-statutory Double Patenting
3. The non-statutory double patenting rejection, make in the previous office action is withdrawn because the terminal disclaimer received on 09/30/2026 has been approved.
Claim Rejections - 35 USC § 103
4. 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.
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 of this title, 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. Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Garrido et al (“Automatic Face Reenactment”, IEEE, 2014, hereinafter “Garrido”)
Regarding claim 1, Garrido discloses a method (the face replacement (facial reenactment) method/system; see abstract), comprising:
receiving, by a computing device: a sequence of frame images generated based on a video (receiving the celebrity target video and the user source video; see “Target” video (the left col.) and “Source” video (the right col.) of fig.1; see section 3); face area parameters corresponding to positions of a face area in a frame image of the sequence of frame images (wherein a facial area including a set of pixels is extracted from each of the 4 frame images generated from the target video; see the third row of fig.1); and facial landmark parameters corresponding to the frame image of the sequence of frame images (“n=66 consistent landmark locations on the mouth, eyes, nose, and face outline” are determined from the user frame image generated from the user video; see the right of the third row of fig.1 and sec. 4, para.1, lines 1-5. It should be noticed that: wherein the user frame image generated from the user video “corresponds to” the target frames generated from the target video), the facial landmark parameters being absent from the frame images (ibid., wherein the 66 landmarks extracted from the user frame image are absent from the three actor frame images), the facial landmark parameters being generated based on information different from the video used to generate the sequence of frame images (ibid., wherein the 66 landmarks extracted from the user frame image of the user video which is different from the target video );
receiving, by the computing device, a source sequence video (see “Source” sequence (the right col.) of fig.1; see section 3);
modifying, by the computing device, based on the facial landmark parameters corresponding to the frame image, the image of the source face to obtain a further face image featuring the source face adopting a facial expression associated with the facial landmark parameters (see Sec.6, para.1: “we transfer the face of the user to the corresponding target frames and create the final composite.” Also, see the middle image in the 4-th row of fig.1; wherein the final composite face image adopts “a facial expression corresponding to the facial landmark parameters” of Obama as shown in the bottom row of the left side of fig.6); and
inserting, by the computing device, the further face image into the frame image at a position determined by the face area parameters associated with the frame image, thereby generating an output frame of an output video (see Sec.3, para.1: “We can produce reenactments for different target videos from only a single source video”. Also see “Reenactment” video shown in the bottom row of fig.1; wherein the final composite reenactment video “blend[s] the source face into the target sequence using seamless cloning” as taught by Garrido in Sec.3, step 3 on the left col. on pg.4323).
As explained above, the mere difference between Garrido and the claimed invention is, Garrido receives a source face sequence video as shown in fig.1, instead of “an image of a source face” recited in the claim. However, the difference is obvious and straightforward. Indeed, Garrido teaches a technique by selecting a source frame image from the source sequence video. See the third row of fig.1 and Sec.3, step 3, on the left col. on pg.4323. Therefore, it would have been obvious at the time before the effective filling date of the claimed invention was made to replace the source sequence video taught by Garrido with an image of a source face as recited in the claim. One of ordinary skill in the art before the effective filling date of the claimed invention was made would have found it obvious to replace the source sequence video taught by Garrido with an image of a source face as recited in the claim since doing this would amount to a simple substitution of one known element (a source frame selected from the inputted source video) for another (a directly inputted source image) to obtain predictable results. Therefore, Garrido suggests or teaches every limitation recited in claim 1, and the claim is unpatentable over Garrido.
Regarding claim 2, 12, Garrido discloses, wherein the facial landmark parameters are generated based on a video featuring a person (see fig.1).
Regarding claim 3, 13, Garrido discloses, wherein the facial landmark parameters are generated based on a user input (see fig.1).
Regarding claim 4, 14, Garrido discloses, wherein the facial landmark parameters are generated based on an animation video (see Sec.2, par.1, lines 5-6: “Such methods are used to animate digital avatars in games, movies and video conferences.”).
Regarding claim 5, 15, Garrido discloses, wherein the facial landmark parameters are generated based on an audio file (Obama’s speech video, a live action video shown in fig.1 and the left side of fig.6).
Regarding claim 6, 16, Garrido discloses, wherein the facial landmark parameters are generated based on a text (Obama’s speech video, a live action video shown in fig.1 and the left side of fig.6).
Regarding claim 7, 17, Garrido discloses, further comprising: receiving, by the computing device, head parameters associated with a size of the face area in the frame image of the sequence of frame images; and modifying, by the computing device, based on the head parameters, the image of the source face to fit the size of the face area (see fig.1 and “Face Reenactment System” in Sec.3).
Regarding claim 8, 18, Garrido discloses, further comprising: receiving, by the computing device, head parameters associated with a rotation of a head to be inserted in the frame image of the sequence of frame images; and modifying, by the computing device, based on the head parameters, the image of the source face to adopt the rotation of the head (see Sec.3, step 3: “The target head pose is transferred to the selected source frames by warping the facial landmarks.”; see Sec.5, para.1: “A central part of our reenactment system is matching the source and target faces under differences in head pose.”).
Regarding claim 9, 19, Garrido discloses, wherein the frame image includes an animal (this feature is obvious for one skilled in the art based on the teaching of Garrido, see Sec.2, par.1, lines 5-6: “Such methods are used to animate digital avatars in games, movies and video conferences.”).
Regarding claim 10, Garrido discloses the method of claim 1, wherein the frame image includes a drawn picture (this feature is obvious for one skilled in the art based on the teaching of Garrido, see Sec.2, par.1, lines 5-6: “Such methods are used to animate digital avatars in games, movies and video conferences.”).
Regarding claim 11, 20, each of which is an inherent variation of claim 1, thus it is interpreted and rejected for the reasons set forth above in the rejection of claim 1.
Response to Arguments
7. Applicant’s arguments, with respects to claims 1, 11 and 20, filed on 09/30/2026, have been fully considered but they are not persuasive.
On page 9 of applicant’s response, applicant argues that Garrido does not teach or suggest all elements of amended independent claim 1, because claim 1 has amended as:
“receiving, by a computing device: a sequence of frame images generated based on a video...; and facial landmark parameters corresponding to the frame image of the sequence of frame images, the facial landmark parameters being absent from the frame images, the facial landmark parameters being generated based on information different from the video used to generate the sequence of frame images”.
(The emphases added by the applicant.)
The examiner respectfully disagrees with the argument. As explained in the rejections of the claims, Garrido discloses
receiving the celebrity target video and the user source video; see “Target” video (the left col.) and “Source” video (the right col.) of fig.1; see section 3; detecting a facial area including a set of pixels is extracted from each of the frame images generated from the target video and the source video; see the third row of fig.1; and extracting n=66 consistent landmark locations from the user frame image generated from the user video; see the right of the third row of fig.1 and sec. 4, para.1, lines 1-5; wherein the user frame image generated from the user video “corresponds to” the target frames generated from the target video; wherein the 66 landmarks extracted from the user frame image are absent from the three actor frame images generated from the target video; wherein the 66 landmarks extracted from the user frame image of the user video which is different from the target video. Thus, Garrido discloses or suggests all elements recited by claim 1, and the applicant’s argument is not persuasive.
Conclusion
8. 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 extension fee 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.
9. Any inquiry concerning this communication or earlier communications from the examiner should be directed to RUIPING LI whose telephone number is (571)270-3376. The examiner can normally be reached 8:30am--5:30pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, HENOK SHIFERAW can be reached on (571)272-4637. 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; 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.
/RUIPING LI/Primary Examiner, Ph.D., Art Unit 2676
