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 § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Yang et al., Physics-Inspired Garment Recovery from a Single-View Image, ACM Transactions on Graphics, November 2018, pages 170(1-14).
Regarding claim 1, Yang discloses a method for extracting clothing assets, comprising: receiving three-dimensional (3D) scan data characterizing a person wearing a garment (page 1, col. 2, 1st paragraph, user selects one of a pre-defined set of avatars or that accurate measurements of their own bodies have be captured via 3D body scans; page 1, col. 2, 3rd paragraph, given only a single photograph of themselves wearing clothing; Fig. 1, original image); processing the scan data to simultaneously (i) identify from the scan data an initial garment pattern and garment material (page 2, col. 1, 3rd paragraph, semantic parse of the garments in the image to identify and localize depicted clothing item; existing garment templates; page 2, col. 2, 1st paragraph, estimating material properties of the garment), and (ii) extract from the scan data an initial pose and an initial body shape (page 2, col. 1, 2nd paragraph, extracting and matching the human body shape and pose in a given input image; Fig. 2); performing a simulation process based on the initial garment pattern, the garment material, the initial pose, and the initial body shape, to compute an initial 3D garment state (page 2, col. 1, 2nd paragraph, set of all possible configurations and dynamical states of garments governed by their respective constitutive laws and simulated by a physically-based cloth model; simulation helps provide additional 3D physical constrains; page 2, col. 2, 1st paragraph obtain the initial 3D garment); performing an optimization process on the initial 3D garment state to simultaneously modify one or more of the initial garment pattern, the garment material, the initial pose, and the initial body shape, resulting in an optimized 3D garment state (page 2, col. 2, 1st paragraph, perform image-guided parameter identification process, which optimizes the garment template parameters based on the reconstructed human body and image information; optimize the material parameters, the body shape and the pose); and extracting, from the optimized 3D garment state, an optimized garment pattern (page 3, col. 1, 1st paragraph, edit the 2D sewing patterns with information extracted from a single-view image, which can be later used to guide the generation of garments of different sizes and styles; Fig. 2, optimized garment parameters).
Regarding claim 2, Yang discloses wherein the scan data comprises a 3D mesh, and processing the scan data comprises performing a segmentation process on the 3D mesh to identify the garment (page 1, col. 2, 3rd paragraph, instead of representing the clothed human as a single mesh, we define a separate mesh for a person’s clothing; page 2, generate a human body mesh for the image; to estimate clothing model, we compute a semantic parse of the garments in the image to identify and localize depicted clothing items; this semantic segmentation is computed automatically).
Regarding claim 3, Yang discloses wherein identifying the initial garment pattern and the garment material comprises selecting a particular garment template from a plurality of garment templates based on identification of the garment (page 2, 2nd paragraph, a collection of all sewing patterns of various common garment types, such as skirts, pants, shorts, t-shirts, tank tops, and dresses, from a database of all garment templates; Fig. 2, initial garment identification; page 7, col. 1, section 5.2, 1st paragraph, for basic garment types, such as skirts, pants, t-shirts, and tank tops, we use one template pattern for each).
Regarding claim 4, Yang disclose wherein the initial garment pattern comprises a plurality of two-dimensional (2D) panels joined by a plurality of seams, and the optimization process modifies the plurality of 2D panels
(Fig. 3, template sewing pattern and parameter space; dashed lines for seams; page 7, col. 1, 3rd paragraph, different sewing patterns result in different garments; to simulate this process; we modify the parameter G, which achieves the same effect; for example, to shorten the skirt, we modify the skirt length parameter).
Regarding claim 5, Yang discloses wherein each 2D panel comprises a plurality of control handles on one or more boundaries of the 2D panel and a plurality of vertices each having coordinates with respect to the plurality of control handles, and the optimization process modifies the coordinates of the control handles to deform the 2D panel (Fig. 3; Yang page 4, col. 2, garment; U is the 2D triangle mesh representing the garment’s pattern pieces; and V is the 3D triangle mesh representation of the garment; for each triangle of the 3D garment mesh V, there is a corresponding one U in the 2D space; for each mesh vertex x ∈ V, such as those lying on a stitching seam in the garment, there might be multiple corresponding 2D vertices u ∈ U; parameter G is the set of parameters that defines the dimensions of the 2D pattern pieces; manipulating the values of the parameters G, garments of different styles and sizes can be modeled: capri pants vs. full-length pants, or tight-fitting vs. loose and flowy silhouettes).
Regarding claim 6, Yang discloses wherein the optimization process uses a loss function that comprises a regularization term to match lengths of the plurality of seams between the plurality of 2D panels and to constrain a curvature of the one or more boundaries of each 2D panel (Page 6, col. 1, 1st paragraph, detect edges using Holistically-Nested edge detection (Xie and Tu 2015) and then smooth the edges by fitting them to low curvature quadric curves; reconnect broken edges by merging those with nearby endpoints and similar orientations; form 2D folds by matching parallel edges).
Regarding claim 7, Yang discloses wherein processing the scan data comprises fitting a parametric body model to the scan data (page 2, col. 2, 2nd paragraph, fit our 3D garment template’s surface mesh onto the human body to obtain; page 5, col. 2, parameterized human model: given the body database, we extract a statistical shape model for human bodies; each world space vertex position p on the human body is parameterized; Fig. 1).
Regarding claim 8, Yang discloses wherein the optimization process uses differentiable simulation (page 6, col. 1, section 4.3, initial garment registration, our initial clothing registration step aims to dress our template garment onto a human body mesh of any pose or shape; Fig. 5; page 7, col. 2, 4th paragraph, stretching forces fstretch are computed by differentiating the stretching energy Ψ).
Regarding claim 9, Yang discloses wherein the scan data comprises a plurality of views of the person from different viewpoints (Fig. 10, different viewpoints; Fig. 12, fixed body shapes with different poses; page 10-11, section 7.2, multi-view reconstruction preserving).
Regarding claim 10, Yang discloses wherein the optimization process estimates the garment material by optimizing for cloth bending properties (page 4, col. 2, Garment: for the clothing parameters, C is the set of material parameters including stretching stiffness and bending stiffness coefficients).
Regarding claim 11, Yang discloses further comprising using the optimized garment pattern to manufacture a physical garment (page 9, section 5.2; modify the classic sewing pattern; classic sewing pattern and template pattern pieces; page 9, section 6.2, 2nd paragraph, provide the optimized design pattern; it is well known in the art to use classic sewing patterns to manufacture physical garments).
Regarding claim 12, Yang discloses wherein the optimization process uses a loss function that comprises a feature matching term to match the optimized garment pattern to the scan data (page 5, col. 2, section 5.1, we initialize the garment sizing parameters; based on the wrinkle information computed from the image, we then optimize both the fabric material parameters C and the sizing parameters of the garment pattern G, till the visual appearance of the simulated cloth (shapes & wrinkles) matches that in the given image; page 6, section 4.3, 2nd paragraph, alignment of the joints of the template garment skeleton with the joints of the human body mesh skeleton; applying a rigid body transformation matrix T on the joint of the garment, where T minimizes the objective function, which Examiner interprets as a loss function in that a loss function minimizes errors and improve performance).
Regarding claims 13- 20, they are rejected based upon similar rational as above claims 1-4, 6, 7, (9 &12), and 10. Yang further discloses a non-transitory computer-readable medium storing a program (page 1, CAD software systems).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Liang et al., U.S. Patent Publication Number 2023/0306699 A1
Liang discloses a method for extracting clothing assets, comprising: receiving three-dimensional (3D) scan data characterizing a person wearing a garment (paragraph 0017, receiving and processing information that is selected or inputted by a human designer via a user interface; paragraph 0015, 3D human body model; may be provided as input to an input to an initial geometric alignment and wrapping process); processing the scan data to simultaneously (i) identify from the scan data an initial garment pattern and garment material (paragraph 0015, flow of garment and body inputs to an initial geometric wrapping process; implementation of a physics-based draping simulation), and (ii) extract from the scan data an initial pose and an initial body shape (paragraph 0021, maps the shape and pose parameters); performing a simulation process based on the initial garment pattern, the garment material, the initial pose, and the initial body shape, to compute an initial 3D garment state (paragraph 0023, initial wrapped garment may then be provided as input to a physics-based draping simulator).
Chen et al., U.S. Patent Number 10/997,779 B2
Chen discloses col. 4, lines 32-33, receive one or more two dimensional images of a model wearing a garment; col. 8, line 51, complete garment texture; col. 8, line 50, different body shape and body poses; col. 4, lines 41-42, simulate the complete 3D garment model being worn on the 3D body of the user.
Guay et al., U.S. Patent Publication Number 2023/0177784 A1
Guay discloses abstract, image augmentation software code, a three-dimensional (3D) shapes library, and/or a 3D poses library. The image processing system also includes a two-dimensional (2D) pose estimation module communicatively coupled to the image augmentation software code. The hardware processor executes the image augmentation software code to provide an image to the 2D pose estimation module and to receive a 2D pose data generated by the 2D pose estimation module based on the image. The image augmentation software code identifies a 3D shape and/or a 3D pose corresponding to the image using an optimization algorithm applied to the 2D pose data and one or both of the 3D poses library and the 3D shapes library, and may output the 3D shape and/or 3D pose.
Krasley et al., U.S. Patent Number 12,524,129 B2
Krasley discloses FIG. 8B, scan, photo icon; col. 11, line 64-65, pattern piece identification module; col. 17, line 23, apparel pattern identification; col. 19, lines 8-11, digital model is being displayed with links related to digital assets, such as the two dimensional pattern pieces; material properties, etc.; col. 6, lines 51-54, identifying a first selected apparel CAD-based model of the plurality of apparel CAD-based models obtained from image data acquired from an imaging device of the computing device; col. 19, lines 12-15, 3D digital models are used to build digital prototypes of garments so the design can be evaluated without having to sew a physical prototype; can further be utilized to judge the fit of a garment on a digital body to make sure the pattern was made correctly; col. 19, lines 12-13, build prototypes of garments.
Santesteban et al., U.S. Patent Publication Number 2024/0331251 A1
Santesteban discloses paragraph 0014, capture 3D scan; cloth layer from the captured 3D scan; paragraph 0014, extract a cloth layer from the captured 3D scan and fit a parametric model to the actor; allows editing the actor’s shape and pose parameters while keeping the same captured garment or even changing it; paragraph 0041, simulation data, such as for example frames of physics-based simulations of multiple bodies wearing the same garment, may be provided as input to a projection module.
Lee et al., U.S. Patent Publication Number 2024/0212279 A1
Lee discloses paragraph 0085, input scan of the computing device; input scan may include 2.5D depth map or 3D full scan of a clothed human body; paragraph 0004, estimate deformation vectors from the initial model, i.e., the surface of a person without clothes; paragraph 0136, perform optimization using the initial correspondence between the SMPL model and input cloud; a smoothness regularization term may be added to the corresponding equations or functions in the time domain to allow the pose parameters of SMPL to change gradually during optimization; paragraph 0138, obtains a pose-dependent base mesh.
Tiwari et al., U.S. Patent Publication Number 2024/0078356
Tiwari discloses paragraph 0053, simulating garments on target body poses; template garment mesh draped over a 3D human body mesh; paragraph 0057, obtain an input data comprising a garment draped on a canonical body pose; paragraph 0068, simulated garment on the target body pose based on the processed encoded garment graph with the updated set of edge feature and updated set of node features; paragraph 0089, varying body shapes and pose, and cloth fabrics; optimizing the code and paralleling the encoding.
Oh et al., U.S. Patent Publication Number 2021/0056755 A1
Oh discloses paragraph 0026, source clothes draped over the 3D source avatar; paragraph 0026, calculate 2D strain information of a 2D pattern corresponding to source clothes draped over the 3D source avatar; identify at least one supplemental material included in the source clothes;
paragraph 0042, source avatar and the target avatar may include properties such as a body size, location coordination of each body portions, and feature points; feature points may correspond to at least one of, for example, both arms, both wrists, left and right bodies, both shoulders, a head, a neck, both legs, left and right lower bodies, both ankles, an armpit, a groin, a pelvis, a hip, a stomach, a chest, both hands, both feet, both elbows, both knees, both fingertips, between both fingers, the back of both hands, the top of both feet, the tips of both toes, and both heels; motion of the virtual garment may be simulated; FIG. 8A, simulation properties; paragraph 0079, may perform grading on the target pattern through an optimization process; paragraph 0101, optimization process; mesh candidate of the 2D target pattern information; paragraph 0079, entire target pattern of the target garments maintains an outline curvature and/or sewing line length ratio of the sources pattern and the like.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Motilewa Good-Johnson whose telephone number is (571)272-7658. The examiner can normally be reached Monday - Friday 6am-2:30pm.
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, Jason Chan can be reached at 571-272-3022. 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.
MOTILEWA . GOOD JOHNSON
Primary Examiner
Art Unit 2616
/MOTILEWA GOOD-JOHNSON/Primary Examiner, Art Unit 2619
Prosecution Insights