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.
Use of indicates a limitation is not explicitly disclosed by the reference alone.
Claim(s) 1-2, 8-10, 12, 16, 23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Seikine (US 2015/0269291) in view of Kuchibotla (US 20190088033)
Claim 1
an image generation method, comprising:
PNG
media_image1.png
839
578
media_image1.png
Greyscale
acquiring a first image including a target object (Sekine, ¶ 38: “The human body Ob2 is photographed by the photographing means attached with the depth sensor to acquire a human body image G2. The human body model D2 representing the shape of the human body Ob2 is generated on the basis of the human body image G2.”);
rendering a target resource model (Sekine, ¶ 37: “It is also possible to photograph the garment Ob1 with photographing means attached with a depth sensor such as a camera or an infrared camera to acquire the garment image G1 and create the garment model D1 with the CG modeling software, the CAD software, or the like on the basis of the garment image G1.); and
fusing the first image and the second image to acquire an effect image for the target object which is added with a virtual resource corresponding to the target garment resource model (Seikine, ¶ 45: “a combined image G3 can be created by superimposing the garment model D4 after the deformation on the human body image G2.”).
Seikine does not explicitly disclose, but Kuchibotla discloses acquiring illumination information of the first image; rendering a target resource model according to the illumination information (¶¶ 20-21: “he lighting may be adjusted by accounting for different lighting used while taking the images. Animated drives help to complete mesh from sixteen key points… he second image is manipulated by using group input values, such as, but not limited to, lighting, color, hue, weight, and dimensions. The dimensions are adjusted using the plurality of measurements obtained by the plurality of key points. The lighting may be adjusted by accounting for different lighting used while taking the images.”)
Before the effective filing date of this application, it would have been obvious to one of ordinary skill in the art to consider illumination as claimed.
One of ordinary skill in the art would have motivation to allow for manual correction and the like in order to better visualize the combined images with consistent lighting. One of ordinary skill in the art would have had a reasonable expectation of success because both references consider a key point based application of a garment image to a model.
Claim 2
Seikine discloses:
constructing a first model corresponding to the target object according to the first image (D2; Seikine, ¶ 74: “as shown in FIG. 8, the human body model D2 is configured by a vertex coordinate list indicating three-dimensional position coordinates concerning a plurality of vertexes of a plurality of polygons representing the shape of a human body and a vertex index list indicating which vertexes are used to form a polygon”);
determining a resource state of the target resource model corresponding to the target object according to the first model (Seikine, ¶ 54: “model D1 is deformed with respect to the vertexes of the garment model D1, at which importance level the garment model D1 should be controlled. As the control weight information, a true value (true/false or 1/0) indicating whether a certain vertex is set as a control point or a value (a value between 0.0 and 1.0) of weight indicating an importance level of control is designated.”);
Seikine does not explicitly disclose, but Kuchibotla discloses the rendering the target resource model according to the illumination information to generate the second image comprises rendering the target resource model according to the resource state of the target resource model corresponding to the target object and the illumination information to generate the second image (¶¶ 20-21: “he lighting may be adjusted by accounting for different lighting used while taking the images. Animated drives help to complete mesh from sixteen key points… he second image is manipulated by using group input values, such as, but not limited to, lighting, color, hue, weight, and dimensions. The dimensions are adjusted using the plurality of measurements obtained by the plurality of key points. The lighting may be adjusted by accounting for different lighting used while taking the images.”)
Before the effective filing date of this application, it would have been obvious to one of ordinary skill in the art to consider illumination as claimed.
One of ordinary skill in the art would have motivation to allow for manual correction and the like in order to better visualize the combined images with consistent lighting. One of ordinary skill in the art would have had a reasonable expectation of success because both references consider a key point based application of a garment image to a model.
Claim 8
Seikine does not explicitly disclose, but Kuchibotla discloses wherein the rendering the target resource model according to the resource state of the target resource model corresponding to the target object and the illumination information to generate the second image comprises:
acquiring material information of the virtual resource (Kuchibotla, ¶ 22: “The present invention builds the material to simulate the saree cloth. This is done using group input values such as color, hue, weight, distance, and gamma to generate a double glossary mix before generating a group output. Multiple gates and routines are involved in generating the material that simulates the saree cloth. The program also creates a lighting system to adjust and account for the different lights that are used in taking the original saree pictures or customer's photograph.”);
rendering the target resource model according to the resource state of the target resource model corresponding to the target object, the illumination information and the material information of the virtual resource to generate the second image (Kuchibotla, ¶ 22: “The present invention builds the material to simulate the saree cloth. This is done using group input values such as color, hue, weight, distance, and gamma to generate a double glossary mix before generating a group output. Multiple gates and routines are involved in generating the material that simulates the saree cloth. The program also creates a lighting system to adjust and account for the different lights that are used in taking the original saree pictures or customer's photograph.”);
Before the effective filing date of this application, it would have been obvious to one of ordinary skill in the art to consider lighting as claimed.
One of ordinary skill in the art would have motivation to allow for lighting matching and accurate representation. One of ordinary skill in the art would have had a reasonable expectation of success because both references consider a key point based application of a garment image to a model.
Claim 9
Seikine does not explicitly disclose, but Kuchibotla discloses wherein before rendering the target resource according to the illumination information, the method further comprises:
displaying a resource selecting interface, at least one resource model being displayed on the garment resource selecting interface (Kuchibolta, ¶ 14: “a user interface module for uploading a first digital image of a user and for selecting a clothing item comprising a second digital image, and an overlay module for overlaying the second digital image of the clothing item on the first digital image of the user.”);
receiving a selection operation input on the resource selecting interface (Kuchibolta, ¶ 14: “a user interface module for uploading a first digital image of a user and for selecting a clothing item comprising a second digital image, and an overlay module for overlaying the second digital image of the clothing item on the first digital image of the user.”); determining a resource model receiving the selection operation as the target resource model (Kuchibolta, ¶ 14: “a user interface module for uploading a first digital image of a user and for selecting a clothing item comprising a second digital image, and an overlay module for overlaying the second digital image of the clothing item on the first digital image of the user.”);
Before the effective filing date of this application, it would have been obvious to one of ordinary skill in the art to consider adjustment as claimed.
One of ordinary skill in the art would have motivation to allow for user interfaces in order to allow selection of different garment options. One of ordinary skill in the art would have had a reasonable expectation of success because both references consider a key point based application of a garment image to a model.
Claim 10
Seikine does not explicitly disclose, but Kuchibotla discloses wherein the method further comprises:
receiving a correction operation on the effect image (Kuchibolta, Fig. 2: “minor adjustment”; Also ¶ 21: “ The overlay module may further generate a simulation of the clothing prior to overlaying. The simulation of the clothing is the second 3-dimensional image. The simulation may be generated by manipulating the second image. The second image is manipulated by using group input values, such as, but not limited to, lighting, color, hue, weight, and dimensions. The dimensions are adjusted using the plurality of measurements obtained by the plurality of key points”);
correcting the effect image in response to the correction operation on the effect image (Kuchibolta; ¶ 20: “The lighting may be adjusted by accounting for different lighting used while taking the images. Animated drives help to complete mesh from sixteen key points. The module further loops through to add additional clothing items and animates the texture mixers to switch textures with each set of thirty seven dimensions.”) .
Before the effective filing date of this application, it would have been obvious to one of ordinary skill in the art to consider adjustment as claimed.
One of ordinary skill in the art would have motivation to allow for manual correction and the like in order to better fit the mode. One of ordinary skill in the art would have had a reasonable expectation of success because both references consider a key point based application of a garment image to a model.
Claim 12
The same teachings and rationales in claim 1 are appliable to claim 12.
Claim 13
Examiner’s Interpretation:
Machine readable media can encompass forms of signal transmission media that falls outside of the four statutory categories of invention. MPEP 2106; citing In re Nuijten, 500 F.3d 1346, 84 USPQ2d 1495 (Fed. Cir. 2007). A claim whose BRI covers both statutory and non-statutory embodiments embraces subject matter that is not eligible for patent protection and therefore is directed to non-statutory subject matter. MPEP 2106.
Claim 13 as drafted recites non-transitory computer-readable storage medium…
The broadest reasonable interpretation of the claimed medium in view of Applicant’s specification covers only eligible subject matter.
Claim Mapping:
The same teachings and rationales in claim 1 are appliable to claim 13.
Claim 16
The same teachings and rationales in claim 2 are appliable to claim 16.
Claim 20
The same teachings and rationales in claim 2 are appliable to claim 20.
Claim 23
Seikine discloses wherein the virtual resource is a virtual garment, and the target resource model is a target garment model (Seikine; ¶ 26, 28: “A garment model D1… The control-point calculating unit 14 calculates, on the basis of the garment model D1, the human body model D2, and the deformation parameters D3, target position coordinates to which points of the garment model D1 should move according to the human body model D2 when the garment is worn on the human body.”).
Claim(s) 3-5, 17-18, 21-22 is/are rejected under 35 U.S.C. 103 as being unpatentable over Seikine (US 2015/0269291) in view of Kuchibotla (US 20190088033) and Fedyukov (US 2021/0049811)
Claim 3
Seikine does not explicitly disclose, but Fedyukov discloses wherein the constructing the first model corresponding to the target object according to the first image comprises:
performing a key point detection on the target object to acquire position information of a plurality of key points of the target object (Fedyukov, ¶ 129, 175: “FIG. 3 shows an articulated model of the human body skeleton, in which red (large) points are included in many key points (landmarks) of the skeleton…The construction of a parametric model may include: [0130] calculation of initial approximation of pose parameters; [0131] refinement of pose parameters; [0132] refinement of pose and shape parameters; [0133] construction of a morphing field graph that allows the transformation of the geometric model from a canonical pose and/or shape into an arbitrary pose and/or shape.”);
acquiring at least one of a body shape and a posture of the target object according to the position information of the plurality of key points (Fedyukov, ¶ 129, 175: : “The construction of a parametric model may include: [0130] calculation of initial approximation of pose parameters; [0131] refinement of pose parameters; [0132] refinement of pose and shape parameters; [0133] construction of a morphing field graph that allows the transformation of the geometric model from a canonical pose and/or shape into an arbitrary pose and/or shape.”);
constructing the first model according to the at least one of the body shape and the posture of the target object (Fedyukov, ¶ 129: “The construction of a parametric model may include: [0130] calculation of initial approximation of pose parameters; [0131] refinement of pose parameters; [0132] refinement of pose and shape parameters; [0133] construction of a morphing field graph that allows the transformation of the geometric model from a canonical pose and/or shape into an arbitrary pose and/or shape.”).
Before the effective filing date of this application, it would have been obvious to one of ordinary skill in the art to shape and pose as claimed.
One of ordinary skill in the art would have motivation to allow for manual correction and the like in order to better visualize the combined images with consistent display. One of ordinary skill in the art would have had a reasonable expectation of success because both references consider a key point based application of a garment image to a model.
Claim 4
Seikine does not explicitly disclose, but Kuchibotla discloses wherein the method further comprises:
receiving a correction operation on the at least one of the body shape and the posture of the first model (Kuchibolta, Fig. 2: “minor adjustment”; Also ¶ 21: “ The overlay module may further generate a simulation of the clothing prior to overlaying. The simulation of the clothing is the second 3-dimensional image. The simulation may be generated by manipulating the second image. The second image is manipulated by using group input values, such as, but not limited to, lighting, color, hue, weight, and dimensions. The dimensions are adjusted using the plurality of measurements obtained by the plurality of key points”);
correcting the at least one of the body shape and the posture of the first model in response to the correction operation on the at least one of the body shape and the posture of the first model (Kuchibolta, Fig. 2: “minor adjustment”; Also ¶ 21: “ The overlay module may further generate a simulation of the clothing prior to overlaying. The simulation of the clothing is the second 3-dimensional image. The simulation may be generated by manipulating the second image. The second image is manipulated by using group input values, such as, but not limited to, lighting, color, hue, weight, and dimensions. The dimensions are adjusted using the plurality of measurements obtained by the plurality of key points”).
Before the effective filing date of this application, it would have been obvious to one of ordinary skill in the art to consider adjustment as claimed.
One of ordinary skill in the art would have motivation to allow for manual correction and the like in order to better fit the mode. One of ordinary skill in the art would have had a reasonable expectation of success because both references consider a key point based application of a garment image to a model.
Claim 5
Seikine does not explicitly disclose, but Kuchibotla discloses wherein the determining the resource state of the target resource model corresponding to the target object according to the first model comprises: constructing a second model corresponding to the target object according to an initial state of the target garment resource model; determining the garment resource state of the target garment resource model corresponding to the target object according to the first model and the second model (Kuchibotla, ¶ 22: “The program also creates a lighting system to adjust and account for the different lights that are used in taking the original saree pictures or customer's photograph. The program maps out 16 key points on the human body to generate the 37 different measurements. Animate the drivers so that the saree is rendered with all 37 different dimensions. The module creates a secondary pose by using the afore mentioned steps. Finally, the module loops through to add additional sarees and animates the texture mixers to switch textures with each set of 37 dimensions. While the initial dimensions of the model are calculated based on the uploaded picture, manual adjustments may be required to set it perfectly. Customers, after making few manual adjustment(s), may save the picture as their profile.”)
Before the effective filing date of this application, it would have been obvious to one of ordinary skill in the art to consider adjustment as claimed.
One of ordinary skill in the art would have motivation to allow for manual correction and the like in order to better fit the mode. One of ordinary skill in the art would have had a reasonable expectation of success because both references consider a key point based application of a garment image to a model.
Claim 17
The same teachings and rationales in claim 3 are appliable to claim 17.
Claim 18
The same teachings and rationales in claim 5 are appliable to claim 18.
Claim 21
The same teachings and rationales in claim 3 are appliable to claim 21.
Claim 22
The same teachings and rationales in claim 5 are appliable to claim 22.
Claim(s) 6, 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Seikine (US 2015/0269291) in view of Kuchibotla (US 20190088033), Fedyukov (US 2021/0049811) and Song (US 2023/0077356)
Claim 6
Seikine does not explicitly disclose, but Song discloses wherein the determining the garment resource state of the target garment resource corresponding to the target object according to the first model and the second model comprises:
generating a sequence of models according to the first model and the second model, the sequence of models including a plurality of models, and the plurality of models gradually changing from the second model to the first model in order (e.g. training sequence of models; ¶ 38: “S130: Generate, according to image features of the first image and image features of the second image, a target appearance flow feature for representing deformation of the target clothes matching a body of the target person, and generate, based on the target appearance flow feature, a deformed image of the target clothes matching the body. Here, the target clothes matching the body may mean that the target clothes are simulated or superimposed on the body image. For example, the target clothes matching the body may refer to a state in which an image of the target clothes is positioned (e.g., superimposed) on a region of an image of the body of the target person. For example, the target clothes matching the body may refer to a state in which an image of the target clothes positioned on the region of the image of the body of the target person conforms to a body shape or a body silhouette of the target person.”);
performing a simulation on the target garment resource model in the initial state based on the first model in the sequence of models to acquire a garment resource state corresponding to the first model (e.g. training sequence of models; ¶ 38: “S130: Generate, according to image features of the first image and image features of the second image, a target appearance flow feature for representing deformation of the target clothes matching a body of the target person, and generate, based on the target appearance flow feature, a deformed image of the target clothes matching the body. Here, the target clothes matching the body may mean that the target clothes are simulated or superimposed on the body image. For example, the target clothes matching the body may refer to a state in which an image of the target clothes is positioned (e.g., superimposed) on a region of an image of the body of the target person. For example, the target clothes matching the body may refer to a state in which an image of the target clothes positioned on the region of the image of the body of the target person conforms to a body shape or a body silhouette of the target person.”);;
performing the simulation on the target garment resource model in garment resource state corresponding to the (n-1)th model based on the nth model in the sequence of models to acquire a garment resource state corresponding to the nth model, n being an integer greater than 1 (iterative training process; ¶ 38: “S130: Generate, according to image features of the first image and image features of the second image, a target appearance flow feature for representing deformation of the target clothes matching a body of the target person, and generate, based on the target appearance flow feature, a deformed image of the target clothes matching the body. Here, the target clothes matching the body may mean that the target clothes are simulated or superimposed on the body image. For example, the target clothes matching the body may refer to a state in which an image of the target clothes is positioned (e.g., superimposed) on a region of an image of the body of the target person. For example, the target clothes matching the body may refer to a state in which an image of the target clothes positioned on the region of the image of the body of the target person conforms to a body shape or a body silhouette of the target person.”);;
determining a garment resource state corresponding to the last model in the sequence of models as the garment resource state of the target garment model corresponding to the target object (e.g. goal state: “For example, the target clothes matching the body may refer to a state in which an image of the target clothes positioned on the region of the image of the body of the target person conforms to a body shape or a body silhouette of the target person.”);
Before the effective filing date of this application, it would have been obvious to one of ordinary skill in the art to consider a sequence of models.
One of ordinary skill in the art would have motivation to allow for manual correction and the like in order to better match clothing. One of ordinary skill in the art would have had a reasonable expectation of success because both references consider a key point based application of a garment image to a model.
Claim 19
The same teachings and rationales in claim 6 are appliable to claim 19.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Seikine (US 2015/0269291) in view of Kuchibotla (US 20190088033) and Dalal (US Patent 8,674,989)
Claim 7
Seikine does not explicitly disclose, but Dalal discloses wherein the rendering the target garment resource model according to the illumination information to generate the second image comprises:
generating a light map corresponding to the first image according to the illumination information; rendering the target garment resource model according to the light map to generate the second image (Dalal; “FIG. 5 illustrates a method for creating shading and lighting effects when implementing a photorealistic imaging system for depicting clothing and apparel, under an embodiment. As an initial process, clothing or apparel may be modeled for shadow creation (510). This step may include modeling clothing by category, or individually. In one embodiment, the clothing is modeled by (i) placing the clothing on a model or mannequin; (ii) illuminating the clothing from two opposite angles (other lighting alignments may also be used, particularly to simulate different kinds of lighting conditions); and (iii) making a light map.”).
Before the effective filing date of this application, it would have been obvious to one of ordinary skill in the art to consider a light map as claimed
One of ordinary skill in the art would have motivation to allow for manual correction and the like in order to better match lighting. One of ordinary skill in the art would have had a reasonable expectation of success because both references consider a key point based application of a garment image to a model.
Additional Prior Art
Additional prior art relevant to Applicant’s disclosure but not relied upon:
He (US 2021/0134056) also considers garment matching:
PNG
media_image2.png
820
604
media_image2.png
Greyscale
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RYAN M GRAY whose telephone number is (571)272-4582. The examiner can normally be reached on Monday through Friday, 9:00am-5:30pm (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, Kee Tung can be reached on (571)272-7794. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/RYAN M GRAY/Primary Examiner, Art Unit 2611
Prosecution Insights