DETAILED ACTION
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 .
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, 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.
Claim(s) 1, 6, 8, 13, 17, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cragg et al., US PGPUB No. 20240273670 A1, hereinafter Cragg, and further in view of Kaku et al., US PGPUB No. 20230377252 A1, hereinafter Kaku.
Regarding claim 13,Cragg discloses a computing device (Cragg; a computing device [¶ 0031-0033 and ¶ 0036], as illustrated within Fig. 1; moreover, image processing apparatus [¶ 0043-0045], as illustrated within Fig. 2) comprising:
an input/output interface configured to receive a user input to request processing an input image and output a recomposed image processed according to the user input (Cragg; an I/O interface configured to receive a user input to request processing an input image and output a recomposed image processed according to the user input [¶ 0034-0035]; moreover, user interface [¶ 0037] and user provided data [¶ 0083-0084], as illustrated within Fig, 5);
a memory to store instructions for processing the input image (Cragg; a memory to store instructions for processing the input image [¶ 0044-0045]; additionally, DB for data handling [¶ 0042] and neural networks implicitly correlate to memory structures for processing input data [¶ 0046-0047]); and
at least one processor configured to execute the instructions (Cragg; at least one processor configured to execute the instructions [¶ 0044-0045]), wherein the instructions cause the at least one processor (Cragg; wherein the instructions [as addressed above] cause the at least one processor to implement [¶ 0044-0045 and ¶ 0072]) to:
receive the user input for a movement of at least one object included in the input image (Cragg; receive the user input for a movement (corresponding to a target dimension) of at least one implicit object (given image content known to one or ordinary skill in the art) included in the input image [¶ 0083-0085]; wherein, a user is able to prompt [¶ 0087-0088 and ¶ 0097]; moreover, when applying the image processing apparatus to geometry modification of an image, a user may adjust an object or manipulate geometry related to the image [¶ 0086]; wherein, an image implicitly includes an object/subject [¶ 0024 and ¶ 0027]), expand the input image in a direction determined based on the movement of the at least one object (Cragg; expand the input image in a direction determined based on the movement of the at least one object [¶ 0088-0089]; wherein, expansion of the image implicitly moves the object within the image [¶ 0092]; additionally, expanded image includes generating new content [¶ 0103-0105]);
determine a generation required area based on the expanded input (Cragg; determine a generation required area based on the expanded input [¶ 0088-0090]; moreover, outpainted regions [¶ 0096-0098]) , wherein the generation required area is an area in which generation of a partial image for the at least one object is required (Cragg; the generation required area is an area in which generation of a partial image for the at least one object is required [¶ 0097-0098]; wherein, an expansion image is generated based in an image (e.g. a base image or primary image) [¶ 0084, ¶ 0088, and ¶ 0092]; in other words, a partial image correlates to origin image data from which to generate from; furthermore, the image data implicitly includes an object/subject [as addressed above]; even further, one or more tiles and portions of an outpainted region [¶ 0119-0122], as illustrated within Fig. 11);
generate an image for the generation required area, by using at least one generative model (Cragg; generate an image for the generation required area by using at least one generative model [¶ 0026 and ¶ 0035]; additionally, diffusion model [¶ 0062-0064]; wherein, outpainted regions [¶ 0088-0089 and ¶ 0097-0099] rely on the use of a diffusion model [¶ 0072, ¶ 0100-0101, and ¶ 0112-0113]); and
output the recomposed image based on the input image and the partial image for the at least one object (Cragg; output the recomposed image based on the input image and the partial image for the at least one object [¶ 0090 and ¶ 0112-0113]).
Cragg fails to explicitly disclose a movement of at least one object.
However, Kaku teaches a movement of at least one object included in the image (Kaku; a movement of at least one object included in the image [¶ 0047-0048]; moreover, moving an object from one plane to another [¶ 0085-0086]); and
expand the image in a direction determined based on the movement of the at least one object (Kaku; expand/extended the image in a direction determined [¶ 0038] based on the movement of the at least one object [¶ 0047-0048]; moreover, extension of a plane [¶ 0007-0009]).
Cragg and Kaku are considered to be analogous art because both pertain to generating and/or managing data in relation with providing media data to a user, wherein one or more computerized units are utilized in order to produce an altered visualization effect.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Cragg, to incorporate a movement of at least one object included in the image; and expand the image in a direction determined based on the movement of the at least one object (as taught by Kaku), in order to provide a realistic user experience (Kaku; [¶ 0005-0006 and ¶ 0019]).
Regarding claim 17, Cragg in view of Kaku further discloses the computing device of claim 13, wherein, in the determining of the generation required area, the instructions further cause the at least one processor (Cragg; [as addressed within parent claim(s)]) to:
determine an area including the at least one object in the expanded input image, as a first object proposal area (Cragg; determine an area including the at least one implicit object in the expanded input image as a 1st object proposal area [¶ 0119-0122], as illustrated within Fig. 11; wherein, Fig. 11 illustrates, one or more proposal areas for expansion which involve at least one implicit object/subject; moreover, one or more tiles are able to be configured for diffusion model [¶ 0097-0098 and ¶ 0100]);
move the at least one object according to the request (Cragg; implicitly move the at least one implicit object according to the request [¶ 0119-0122]; wherein, the object within an image is implicitly moved based on an expansion of an overlapping region [¶ 0084 and ¶ 0088-0089]);
determine a second object proposal area corresponding to the moved at least one object, based on the first object proposal area (Cragg; determine a 2nd object proposal area corresponding to the implicit moved at least one object based on the 1st object proposal area [¶ 0119-0122], as illustrated within Fig. 11; wherein, the object within an image is implicitly moved based on an expansion of an overlapping region [¶ 0084 and ¶ 0088-0089]; in other words, determining neighboring regions for expansion); and
determine the generation required area based on the second object proposal area (Cragg; determine the generation required area based on the 2nd object proposal area [¶ 0112-0113 and ¶ 0121-0122]; wherein, use of a diffusion model [¶ 0072 and ¶ 0100-0101] in relation with outpainted regions [¶ 0088-0089 and ¶ 0097-0099]).
Kaku further teaches movement of an object from one area to another area (Kaku; [¶ 0038 and ¶ 0047-0048]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Cragg as modified by Kaku, to incorporate movement of an object from one area to another area (as taught by Kaku), in order to provide a realistic user experience (Kaku; [¶ 0005-0006 and ¶ 0019]).
Regarding claim 20, Cragg in view of Kaku further disclose the computing device of claim 13, wherein, in the generating of the image for the generation required area, the instructions further cause the at least one processor (Cragg; [as addressed within the parent claim(s)]) to:
generate a prompt based on at least one of information about a position of the generation required area (Cragg; generate a prompt based on at least one of information about a position of the generation required area [¶ 0119-0122]; moreover, outpainted regions [¶ 0097]; moreover, a ML model includes prompt generation network [¶ 0056-0058] associated with a diffusion model [¶ 0059 and ¶ 0072]; wherein, prompt based on information [¶ 0023, ¶ 0025, and ¶ 0030]; still further, inferred prompt [¶ 0035]), information about a type of the at least one object, or information about a background including the generation required area (Cragg; information about a type of the at least one implicit object (the implicit object as addressed within the parent claim(s)) [¶ 0120-0122]; wherein, a prompt can be generated based on metadata (e.g. location, time, color, lighting info) associated with the image [¶ 0023]); and
input the generated prompt to the at least one generative model (Cragg; input the generated prompt to the at least one generative model [¶ 0026 and ¶ 0072]).
Regarding claim 1, the rejection of claim 1 is addressed within the rejection of claim 13, due to the similarities claim 1 and claim 13 share, therefore refer to the rejection of claim 13 regarding the rejection of claim 1. Although, claim 1 and claim 13 may not be identical, they are considerably comparable or substantially equivalent given their overlapping subject matter. Thus, it is reasonable to reject claim 1 based on the teachings and rational in relation with the prior art within the rejection of claim 13.
Regarding claim 6, Cragg in view of Kaku further discloses the method of claim 1, wherein the determining of the generation required area comprises determining the area in which generation of the partial image of the at least one object is required (Cragg; the determining of the generation required area [as addressed within the parent claim(s)] comprises determining the area in which generation of the partial image of the at least one object is required [¶ 0119-0122]; moreover, outpainted regions [¶ 0097]), as the generation required area, based on a size of the at least one object and a direction of the movement of the at least one object (Cragg; the generation required area [as addressed above] (is) based on an implicit size (given objects have dimensionality) of the at least one object and a direction of the movement of the at least one object [¶ 0112-0113 and ¶ 0121-0122]; additionally, modification of an object according to skew [¶ 0027 and ¶ 0127-0128] and/or aspect [¶ 0130-0131 and ¶ 0133]; wherein, movement is in accordance with the outpainted regions [¶ 0088-0089 and ¶ 0097-0098]).
Kaku teaches a direction of movement of an object (Kaku; a direction of movement of an object [¶ 0038 and ¶ 0047-00480]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Cragg as modified by Kaku, to incorporate a direction of movement of an object (as taught by Kaku), in order to provide a realistic user experience (Kaku; [¶ 0005-0006 and ¶ 0019]).
Regarding claim 8, the rejection of claim 8 is addressed within the rejection of claim 17, due to the similarities claim 8 and claim 17 share, therefore refer to the rejection of claim 17 regarding the rejection of claim 8.
Regarding claim 11, the rejection of claim 11 is addressed within the rejection of claim 20, due to the similarities claim 11 and claim 20 share, therefore refer to the rejection of claim 20 regarding the rejection of claim 11.
Regarding claim 12, the rejection of claim 12 is addressed within the rejection of claim 13, due to the similarities claim 12 and claim 13 share, therefore refer to the rejection of claim 13 regarding the rejection of claim 12. Although, claim 12 and claim 13 may not be identical, they are considerably comparable or substantially equivalent given their overlapping subject matter. However, the subject matter/limitations not addressed by claim 13 is/are addressed below.
Cragg discloses a non-transitory computer-readable recording medium storing instructions (Cragg; a non-transitory computer-readable recording medium storing instructions [¶ 0044-0045]).
(further refer to the rejection of claim13)
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cragg in view of Kaku as applied to claim(s) 1 above, and further in view of Kulkarni et al., US PGPUB No. 20230169632 A1, hereinafter Kulkarni.
Regarding claim 7, Cragg in view of Kaku further discloses the method of claim 1, wherein the determining of the generation required area (Cragg; [as addressed within parent claim(s)]) comprises:
identifying the at least one object (Cragg; implicitly identifying (given modification thereof) the at least one object [¶ 0112-0113 and ¶ 0121-0122]; wherein, modification correlates with objects/subjects of an image associated with skew [¶ 0127-0128] and/or aspect [¶ 0130-0131 and ¶ 0133]); and
based on a result of the identifying, determining the area in which generation of an image of the at least one object is required, as the generation required area (Cragg; determining the area in which generation of an image of the at least one object is required, as the generation required, based on a result of the implicit identifying area [¶ 0112-0113 and ¶ 0121-0122]; moreover, regions are determined in relation with the operations of generation of the model [¶ 0027 and ¶ 0100-0101]).
Cragg as modified by Kaku fails to explicitly disclose identification of an object.
However, Kulkarni teaches identification of an object (Kulkarni; [¶ 0015-0016]).
Cragg in view Kaku and Kulkarni are considered to be analogous art because both pertain to generating and/or managing data in relation with providing media data to a user, wherein one or more computerized units are utilized in order to produce an altered visualization effect.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Cragg as modified by Kaku, to incorporate identification of an object (as taught by Kulkarni), in order to provide imaging that improve saliency and realism which is not resource intensive (Kulkarni; [¶ 0002-0004]).
Allowable Subject Matter
Claims 2-5, 9-10, 14-16, and 18-19 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.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Refer to PTO-892, Notice of Reference Cited for a listing of analogous art.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Charles Lloyd Beard whose telephone number is (571)272-5735. The examiner can normally be reached Monday - Friday, 8:00 AM - 5: 00 PM, alternate Fridays 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, Tammy Goddard can be reached at (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.
CHARLES LLOYD. BEARD
Primary Examiner
Art Unit 2611
/CHARLES L BEARD/Primary Examiner, Art Unit 2611
Prosecution Insights