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 .
Response to Amendment
The amendment filed on 8/4/26 has been entered and made of record. Claims 1, 10-11 and 14 are amended. Claims 9 and 18 are cancelled. Claims 1-8, 10-17 and 19-20 are pending.
Response to Arguments
Applicant’s arguments with respect to claims 1 and 14 have been considered but they are moot because the arguments do not apply to the references being used in the current rejection.
Claim Rejections - 35 USC § 103
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.
Claims 1-6, 8, 14-15 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Canales et al. (Real-Time Conversational Gaze Synthesis for Avatars, In ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG ’23), November 15–17, 2023) in view of Colburn et al. (The Role of Eye Gaze in Avatar Mediated Conversational Interfaces), Peters et al. (A head movement propensity model for animating gaze shifts and blinks of virtual characters, cited by Canales) and Melzer (US 10,254,544 B1).
As to Claim 1, Canales teaches A method of determining conversational gaze control for computer animation of a character (Canales, Abstract), the method executed on a processing unit, the method comprising:
receiving transcripted speech audio (Canales discloses “an Audio-Technica AT2020 microphone recorded audio in mono, sampled at 44.1kHz” at p. 2);
outputting the trajectories of head motion and gaze for computer animation of the character (Canales discloses “In our work, we focus on developing and evaluating a data-driven approach for animating the eyes of a virtual avatar based on the head motion and audio during a dyadic face-to-face conversation.” at p. 2.)
Canales doesn’t explicitly teach gaze state machine. The combination of Colburn further teaches following limitations:
determining time sequences of gaze transition targets for a series of time-steps using a state machine that resolves between direct focus and aversion at each time-step (Colburn discloses “The stochastic eye gaze models we have developed are summarized in the hierarchical state machine diagrams shown in Figures 1 through 4” under section Hierarchical State Machine; see also Fig 2 below:
PNG
media_image1.png
607
563
media_image1.png
Greyscale
).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the invention of Canales with the teaching of Colburn so as to use gaze state machine to analyze the stochastic eye gaze models (Colburn, p. 4).
The combination of Peters and Melzer further teaches following limitations:
determining trajectories of head motion and gaze of the character for each timestep using the determined gaze transition targets, wherein determining the trajectories of head motion and gaze comprises optimizing for a head rotation to a shift in gaze and interpolating a sequence of head and eye targets using a motion generator (Canales discloses “To this end, we captured the head motion, eye motion, and audio of several two-party conversations and trained an RNN-based model to predict where an avatar looks in a two-person conversational scenario” in Abstract; “there are several methods that synthesize or retarget gaze based on the location of gaze targets or the visual saliency of the virtual scene. Peters et al. [2010] developed a gaze shift model that animates the head, eyes, and blinks of a character based on the gaze target location and a parameter specifying the tendency the character moves their head” at p. 2; “We then use the confidence for each sample (a value between 0 and 1, provided by Pupil [Kassner et al. 2014]), to linearly interpolate the gaze angles between high confidence (c > 0.9) samples within each conversation” at p. 3. Here, it is obvious that the eye interpolation may include the interpolation of head movement. For example, Peters discloses “At this point, a straight forward spherical linear interpolation operation may be conducted for each of the head and eyes, between their initial and final orientations.” at p. 4. Colburn also discloses “While we track the user’s gaze in our study and draw on this information as input to the simulated gaze model for the avatar” at p. 3. Melzer further discloses “Therefore, when an eye movement is detected by the eye movement module 210, a corresponding head movement may be predicted… a head orientation module 218 configured to estimate the head movement based on the eye movement” in C7L57-67.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the invention of Canales and Colburn with the teaching of Peters to explain the interpolation of eye and head movement. The motivation of combining the teaching of Melzer is that a head orientation module can be configured to estimate the head motion in response to the eye motion (Melzer, C8L33-34).
As to Claim 2, Canales in view of Colburn, Peters and Melzer teaches The method of claim 1, further comprising receiving directorial inputs from a user that are embedded within the transcripted speech audio (Canales discloses “created a model that generated both head and eye motion based only on speech input for two party conversations” at p. 2. Colburn also discloses “The microphone input along with the subject’s eye gaze if fed into the eye gaze model described above to drive the eye gaze of the avatar” at p. 7.)
As to Claim 3, Canales in view of Colburn, Peters and Melzer teaches The method of claim 2, wherein the directorial inputs comprise one of look-at tags to amplify salience of an object, directional tags to specify ego-centric aversion behavior, or override tags to force focus or aversion behaviour (Colburn discloses “Each of these sub-states is labeled with either one or two numbers. The (0) state indicates that the avatar is gazing away from the other. State (1,0) indicates the avatar is looking at the other, but that the other is looking away. State (1,1) is one of mutual gaze… Within the other speaking state there are now three targets for gaze: away from anyone, towards the speaker, and towards a non-speaker” at p. 5, see also Fig 1-4.)
As to Claim 4, Canales in view of Colburn, Peters and Melzer teaches The method of claim 1, further comprising determining visually salient portions of a setting for the computer animation to determine locations for the gaze of the character (Canales discloses “a saliency-based gaze behavior model in a virtual conversational scenario… In addition to communication specific gaze behavior models, there are several methods that synthesize or retarget gaze based on the location of gaze targets or the visual saliency of the virtual scene” at p. 2.)
As to Claim 5, Canales in view of Colburn, Peters and Melzer teaches The method of claim 1, wherein determining the time sequences of gaze transition targets comprises determining a speech-based probability indicating whether to avert the gaze of the character from a conversational partner (Colburn teaches gaze transition targets at Fig 1-4. Canales discloses “Iwao et al. [2012; 2013] synthesized the more subtle eye movements that occur during fixations using probability models derived from captured gaze data from two party conversations” at p. 2.)
As to Claim 6, Canales in view of Colburn, Peters and Melzer teaches The method of claim 5, wherein the speech based probability is determined using a recurrent neural network model, the recurrent neural network model taking as input prosodic audio features and relative timing of speaking and listening turns obtained from the transcripted speech audio (Canales discloses “For example, Klein et al. [2019] used an RNN to animate a character’s upper-body as it follows a moving gaze target in real-time… To model gaze direction based on motion and speech inputs, we trained a recurrent neural network (RNN), which can capture temporal relations, on a dataset consisting of two-party conversations” at p. 2. Colburn, section “The Role of Eye Gaze in Conversation” and “Timing of Transitions Between Sub-States”.)
As to Claim 8, Canales in view of Colburn, Peters and Melzer teaches The method of claim 5, wherein transitions of the state machine are determined based on one or more of the speech-based probability, a visual salience of each scene object, and a gaze state of a conversational partner (Colburn, Fig 1-4. Canales discloses “Iwao et al. [2012; 2013] synthesized the more subtle eye movements that occur during fixations using probability models derived from captured gaze data from two party conversations” at p. 2.)
Claim 14 recites similar limitations as claim 1 but in a system form. Therefore, the same rationale used for claim 1 is applied.
Claim 15 is rejected based upon similar rationale as Claim 5.
Claim 17 is rejected based upon similar rationale as Claim 8.
Claims 7 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Canales in view of Colburn, Peters and Melzer, further in view of Lee (JP3659181B2).
As to Claim 7, Canales in view of Colburn, Peters and Melzer teaches The method of claim 4, wherein, during direct focus, look-at-points are generated on a conversational partner, and wherein, during aversion, look-at-points are generated using a random walk algorithm based on scene salience (Colburn teaches gaze state machine in Fig 1-4. Lee further discloses “The random walk algorithm of the embodiment of the present invention using node-seed distance information to identify penalties used in calculating transition probabilities for random walks” in [0070].)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the invention of Canales, Colburn, Peters and Melzer with the teaching of Lee so as to use node-seed distance information to identify penalties used in calculating transition probabilities for random walks (Lee, [0070]).
Claim 16 is rejected based upon similar rationale as Claim 7.
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Canales in view of Colburn, Peters and Melzer, further in view of Miklos et al. (US 2008/0130950 A1).
As to Claim 11, Canales in view of Colburn, Peters and Melzer teaches The method of claim 1, wherein the motion generator comprises interpolation of a sequence of target head and eye angles determined by summing a sequence of sub-movements (Miklos discloses “In such matter, by generating interpolation data, the interpolators may be able to determine a gaze angle of the eye, based on interpolation…” in [0027]; “In step 62, the tracking algorithm of the software may be applied, utilizing the custom template and the eye image at that point in time ( or frame), to determine the real-time, two-dimensional position of a portion of the operator's eye, such as a pupil, within the frame image. In step 64, the tracking algorithm software may use the interpolating data of step 56 in order to determine the operator's real-time eye gaze angle at the operator's eye position determined in step 62” in [0028].)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the invention of Canales and Colburn with the teaching of Miklos so as to interpolate head movement and eye rotation to determine a real-time eye gaze angle with the corresponding head movement.
Claims 12 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Canales in view of Colburn and Dunlop (US 2008/0091122 A1).
As to Claim 12, Canales in view of Colburn, Peters and Melzer teaches The method of claim 1, further comprising adding rhythmic head motion to the trajectory of the head motion (Canales discloses amplitude saccades at p. 3; “parameters, including saccade speed, magnitude, and frequency” at p. 4-5. Here, Canales doesn’t directly use claim language. Dunlop disclose “wherein if the analysis of the motion signal determines that the motion includes rhythmic, repetitive motion of the limbs, head, or trunk, a determination is made” in claim 54.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the invention of Canales and Colburn with the teaching of Dunlop so as to detect rhythmic head motion by analysis on speed, amplitude or frequency etc.
Claim 19 is rejected based upon similar rationale as Claim 12.
Claims 13 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Canales in view of Colburn, Peters and Melzer, further in view of Ressemann et al. (US 2024/0398302 A1).
As to Claim 13, Canales in view of Colburn teaches The method of claim 9. The combination of Ressemann further teaches altering fixation of the trajectory of the gaze with eye rotations where a gaze fixation interval is longer than a predetermined time interval (Ressemann discloses “In certain other embodiments, a patient's point-of-gaze data (e.g., visual fixation data) is analyzed over a predetermined time period (e.g., over multiple sessions spanning several months) to identify a decline, increase, or other salient change in visual fixation (e.g., point-of-gaze data that initially corresponds to that of typically-developing children changing to more erratic point-of-gaze data corresponding to that of children…” in [0330].)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the invention of Canales and Colburn with the teaching of Ressemann so as to change the fixation of the gaze based on meeting a specific condition.
Claim 20 is rejected based upon similar rationale as Claim 13.
Allowable Subject Matter
Claim 10 is 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.
Conclusion
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 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 date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WEIMING HE whose telephone number is (571)270-1221. The examiner can normally be reached Monday-Friday, 8:30am-5:00pm.
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, Tammy Goddard can be reached on 571-272-7773. 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.
/Weiming He/
Primary Examiner, Art Unit 2611
Prosecution Insights