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 Applicant’s Arguments
Applicant’s arguments filed May 21, 2026 have been fully considered, but they are not deemed to be persuasive based on the new reference of OSBAND et al (US 2017/0032245). Specifically, Applicant argues that “Wu's edits of a single texture do not teach or suggest using a mesh of a target object and a 3D covering, let alone using such objects as claimed, e.g., for reward and penalty generation based on whether one can be seen through the other. Wu’s geometry phase (e.g., Figure 2) teaches a mesh of the 3D target object (e.g., 3DMM-based mesh) and the 3D covering is the 3D Batman mask (e.g., figures 1 and 10); furthermore, for reward and penalty generation based on whether one can be see through the other (i.e., the claimed “at least one reward in model generation is established for being able to see parts of the target object through one or more holes of the 3D covering that should be seen and for not being able to see parts of the target object through the 3D covering that should not be seen and at least one penalty in model generation is established for not being able to see parts of the target object through the 3D covering that should be seen and for being able to see parts of the target object through the one or more holes of the 3D covering that should not be seen”), Osband teaches the reinforcement learning process (e.g., Osband, page 10, claim 1) in which “a reinforcement learning is a type of machine learning where an autonomous agent learns to make optimal decisions by interacting with an environment through trial and error, aiming to maximize cumulative rewards (i.e., Numerical feedback from the environment indicating the success or failure of an action). Specifically, Osband’s claim 1 comprises “apply a reinforcement learning process to the deep neural network where the reinforcement learning process includes: receive a set of observed data and a set artificial data, for each of one or more episodes: sample from a set of data that is a union of the set of observed data and the set of artificial data to generate set of training data” (equivalent to Applicant claimed “target object, a union of ‘covered and not covered zones”); “for each time step in each one or more episode: determine a state of the system for a current time step from the set of training data; select an action based on the determined state of the system and a policy mapping actions to the state of the system; determine results for the action including a reward and a transition state that result from the selected action” (equivalent to Applicant claimed “reward and penalty generation based on whether one can be see through the other” (i.e., the claimed “at least one reward in model generation is established for being able to see parts of the target object through one or more holes of the 3D covering that should be seen and for not being able to see parts of the target object through the 3D covering that should not be seen and at least one penalty in model generation is established for not being able to see parts of the target object through the 3D covering that should be seen and for being able to see parts of the target object through the one or more holes of the 3D covering that should not be seen”)). It would have been obvious to implement a reinforcement learning (Osband’s teaching) in the mask generation to configure Wu’s method as claimed. Thus, the claimed invention as represented in the claims does not represent a patentable distinction over the art of record.
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 (i.e., changing from AIA to pre-AIA ) 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 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-8, and 21-22 are rejected under 35 U.S.C. 103 as being unpatentable over WU et al (Text-Guided 3D Face Synthesis - From Generation to Editing) in view of OSBAND et al (US 2017/0032245).
As per claim 1, Wu teaches the claimed "method" comprising: "using a computer, associating plural zones on a mesh of a target object with respective indications each indicating whether the respective zone is to be covered or not covered by a 3D covering to be generated" (Wu, 3.3. Self-guided Consistency Preserved Editing - A key observation in addressing this issue is that the weight of consistency should vary in different regions: For regions associated with editing instructions, a lower level of consistency should be maintained as we prioritize the editing effects. Conversely, for irrelevant regions, a higher level of consistency should be ensured; figure 2 - 3DMM-based mesh) (Noted: the masked (i.e.. covered) region has lower level of consistency; in other words, the masked region is most effected by the editing); "using coverage or non-coverage of the zones as a model of the 3D covering is to be generated" (Wu, 3.3. Self-guided Consistency Preserved Editing - given the instruction "let her wear a Batman eyemask", we desire the eyemask effect near the eyes region while keeping the rest of the face unchanged) (Noted: the claimed "covered" zone is equivalent to Wu's eyemask region which is around, but not include, the eyes region, and the claimed "uncovered" zone is equivalent to Wu's remaining region of the face which is unchanged); and "outputting an image of the 3D head covering" (Wu, figure 4 - Visualization of the edited face, the cross-attention score for token "mask" and the consistency weight Ci during iterations in editing). It is noted that Wu's consistency establishment of the unmask (i.e., should be seen) and mask (i.e., should not be seen) regions suggests the claimed "at least one reward in model generation is established for being able to see parts of the target object through one or more holes of the 3D covering that should be seen and for not being able to see parts of the target object through the 3D covering that should not be seen and at least one penalty in model generation is established for not being able to see parts of the target object through the 3D covering that should be seen and for being able to see parts of the target object through the one or more holes of the 3D covering that should not be seen" (Wu, 3.3. Self-guided Consistency Preserved Editing - A key observation in addressing this issue is that the weight of consistency should vary in different regions: For regions associated with editing instructions, a lower level of consistency should be maintained as we prioritize the editing effects. Conversely, for irrelevant regions, a higher level of consistency should be ensured. The attention scores introduce the association between different image regions and specific textual tokens); furthermore, Osband teaches the reinforcement learning process (e.g., Osband, page 10, claim 1) in which “a reinforcement learning is a type of machine learning where an autonomous agent learns to make optimal decisions by interacting with an environment through trial and error, aiming to maximize cumulative rewards (i.e., Numerical feedback from the environment indicating the success or failure of an action). Specifically, Osband’s claim 1 comprises “apply a reinforcement learning process to the deep neural network where the reinforcement learning process includes: receive a set of observed data and a set artificial data, for each of one or more episodes: sample from a set of data that is a union of the set of observed data and the set of artificial data to generate set of training data” (equivalent to Applicant claimed “target object, a union of ‘covered and not covered zones”); “for each time step in each one or more episode: determine a state of the system for a current time step from the set of training data; select an action based on the determined state of the system and a policy mapping actions to the state of the system; determine results for the action including a reward and a transition state that result from the selected action” (equivalent to Applicant claimed “reward and penalty generation based on whether one can be see through the other” (i.e., the claimed “at least one reward in model generation is established for being able to see parts of the target object through one or more holes of the 3D covering that should be seen and for not being able to see parts of the target object through the 3D covering that should not be seen and at least one penalty in model generation is established for not being able to see parts of the target object through the 3D covering that should be seen and for being able to see parts of the target object through the one or more holes of the 3D covering that should not be seen”)). It would have been obvious to implement a reinforcement learning (Osband’s teaching) in the mask generation to configure Wu’s method as claimed. The motivation of "reward and penalty" is to establish the consistency of the masked regions and not- masked regions for the texturing of the face putting on a mask.
Claim 2 adds into claim 1 "penalizing the model for extending beyond an outer bound" (Wu, page 5, column 2, Consistency Preservation Regularization - With the consistency weight Ci in hand, we propose a region-specific consistency preservation regularization in the UV domain to encourage consistency between faces before and after editing in both texture and geometry; Osband, page 10, column 1, claim 1 - determine results for the action including a reward and a transition state that result from the selected action).
Claim 3 adds into claim 1 "generating the 3D head covering from a default mask" (Wu, Figure 10 - Batman eyemask).
Claim 4 adds into claim 1 "adding a foundation mask model to a final generation of the 3D head covering to cover up any remaining holes" (Wu, 3.3. Self-guided Consistency Preserved Editing - A key observation in addressing this issue is that the weight of consistency should vary in different regions: For regions associated with editing instructions, a lower level of consistency should be maintained as we prioritize the editing effects. Conversely, for irrelevant regions, a higher level of consistency should be ensured) (Noted: By defining a mask region of low level of consistency which covers up the facial holes (e.g., eyes, ears, noses, ...), the Wu model would generate a foundation mask covers up all the facial holes).
Claim 5 adds into claim 1 "associating a first zone of the plural zones with a respective first indication indicating that the first zone is to be covered, the first indication being associated with a first weight" (Wu, 3.3. Self-guided Consistency Preserved Editing - A key observation in addressing this issue is that the weight of consistency should vary in different regions: For regions associated with editing instructions, a lower level of consistency should be maintained as we prioritize the editing effects. Conversely, for irrelevant regions, a higher level of consistency should be ensured) (Noted: assign a low level of consistency weight for a zone to indicate that zone to be covered, or high prioritized editing effect).
Claim 6 adds into claim 5 "associating a second zone of the plural zones with a respective second indication indicating that the second zone is to be covered, the second indication being associated with a second weight" (Wu, 3.3. Self-guided Consistency Preserved Editing - A key observation in addressing this issue is that the weight of consistency should vary in different regions) (Noted: assign multiple levels of consistency associated with different zones to indicate those zones with different prioritized editing effects).
Claim 7 adds into claim 6 "associating a third zone of the plural zones with a respective third indication indicating that the third zone is not to be covered, the third indication being associated with a respective weight that is the same as the first or second weights" (Wu, 3.3. Self-guided Consistency Preserved Editing - A key observation in addressing this issue is that the weight of consistency should vary in different regions; 4.2. Synthesis Results - Furthermore, it enables flexible editing operations, such as independent manipulation of geometry and texture, as well as sequential editing) (Noted: assign multiple levels of editing effects to different regions in which a not-covered region associated with an "area" weight which has the same as the first or second weights of the covered regions).
Claim 8 adds into claim 6 "a third zone of the plural zones with a respective third indication indicating that the third zone is not to be covered, the third indication being associated with a respective weight that is not the same as the first or second weights" (Wu, 3.3. Self-guided Consistency Preserved Editing - A key observation in addressing this issue is that the weight of consistency should vary in different regions; 4.2. Synthesis Results - Furthermore, it enables flexible editing operations, such as independent manipulation of geometry and texture, as well as sequential editing) (Noted: assign multiple levels of editing effects to different regions in which a not-covered region associated with a weight which is different than the first or second weights of the covered regions).
Claims 21 and 22 claim a non-transitory computer storage media encoded with computer program instructions and a system based on the method of claims 1-8; therefore, they are rejected under a similar rationale.
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 PHU K NGUYEN whose telephone number is (571)272-7645. The examiner can normally be reached M-F 8-5pm.
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.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Daniel F. Hajnik can be reached at (571) 272-7642. 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.
/PHU K NGUYEN/Primary Examiner, Art Unit 2616
Prosecution Insights