Custom-fit versions of knitted articles are produced according to digital representations of objects for which the articles are to be manufactured. The digital representations, optionally augmented by surface fitting algorithms, allow for accurate scaling of pattern-specified stitch counts for pattern elements representing the article taking into account wales and courses densities for the material(s) from which the article is to be made. Displayed dimensionally-accurate representations of the custom-fit articles allow for user-specified style and fit preferences to be made and a final digital pattern of the article to be produced. Machine instructions representing pattern pieces to be knitted are automatically produced from the final digital pattern of the article for a target computerized knitting machine and the custom-fit article then manufactured according to the machine instructions.

In an embodiment, a method for optimizing computer machine learning includes receiving an optimization goal. The optimization goal is used to search a database of base option candidates (BOC) to identify matching BOCs that at least in part matches the goal. A selection of a selected base option among the matching BOCs is received. Machine learning prediction model(s) are selected based at least in part on the goal to determine prediction values associated with alternative features for the selected base option, where the model(s) were trained using training data to at least identify weight values associated with the alternative features for models. Based on the prediction values, at least a portion of the alternative features is sorted to generate an ordered list. The ordered list is provided for use in manufacturing an alternative version of the selected base option with the alternative feature(s) in the ordered list.

A tool allows a user to create new designs for apparel and preview these designs in three dimensions before manufacture. Software and lasers are used in finishing apparel to produce a desired wear pattern or other design. Based on a laser input file with a pattern, a laser will burn the pattern onto apparel. With the tool, the user will be able to create, make changes, and view images of a design, in real time, before burning by a laser. The tool can be accessed or executes via a Web browser.

Systems and methods configured to determine appearance of woven and knitted textiles at the ply-level are presented herein. Exemplary embodiments may: obtain an input pattern of a textile, the input pattern comprising a two-dimensional weave pattern; obtain appearance information, the appearance information including one or more of color, transparency, or roughness; determine ply curve geometry based on ply-level fiber details making up individual plys; generate an image simulating an appearance of the textile based on the two-dimensional weave pattern, the appearance information, and the ply curve geometry so that the image simulating the appearance of the textile takes into account the ply-level fiber details; and/or perform other operations.

Systems and methods generating textiles with repeating design elements based at least in part on Voronoi diagrams are provided. In one example implementation, the method can include generating a plurality of seed points in a graphic area. The seed points are utilized to create a Voronoi diagram. A Voronoi diagram is thereafter propagated within the graphic area based upon the seed points. The method also includes receiving a first user input defining a design area. The design area includes a plurality of boundaries within the graphic area. The design area is then correlated to a textile segment and a textile design is generated by replicating the cells in the design area. The cells that intersect the boundaries of the design area are replicated with identical instances placed at the adjacent sides of the design area and the corners of the design area.

Modeling cross-sections of yarn may include receiving yarn simulation input comprising a descriptive model of a general curvature followed by the yarn, providing a plurality of fibers distributed radially from the center of a ply, setting a base position based on parameters, applying a strain model to simulate the effect of stretch forces applied to the yarn, and outputting a yarn model indicating position and directionality of fibers in the yarn. The technology also relates to real-time modeling of a garment comprising a fabric. For instance, real-time modeling of a garment may include providing an input associated with one or more parameters of the fabric, receiving frames of a computer simulated garment, the computer simulated garment including a simulation of the fabric, the fabric simulation including yarns simulated based on a yarn model.

Systems and methods are provided for machine learning-based rendering of a clothed human with a realistic 3D appearance by virtually draping one or more garments or items of clothing on a 3D human body model. The machine learning model may be trained to drape a garment on a 3D body mesh using training data that includes a variety 3D body meshes reflecting a variety of different body types. The machine learning model may include an encoder trained to extract body features from an input 3D mesh, and a decoder network trained to drape the garment on the input 3D mesh based at least in part on spectral decomposition of a mesh associated with the garment. The trained machine learning model may then be used to drape the garment or a variation of the garment on a new input body mesh.

The present invention is generally directed to systems and methods for preparing and producing a custom-fitted face mask, including, as non-limiting examples, a CPAP nasal mask and a CPAP full face mask. At least one embodiment of the invention utilizes infrared (IR) lasers, such as, for example, those found on smartphone cameras, in order to generate a 3D point cloud model of an individual's face. This point cloud model is then used to produce a custom face mask cushion, which is used to customize a generic face mask to conform to the user's specific facial geometry.

Computer based systems and methods for designing and manufacturing consumer products, including knit footwear uppers, and the like. The system provides digital controls for the customization of knitted components, including complex multi-structured knitted components. The system simulates deformations of knit structures and allows the user to control and visualize compensations in the structure(s) of the knitted component to better match between an intended knit design and the actual physical knitted component outcome. The system may manufacture/fabricate a knitted component based on the predicted/estimated deformation behavior of the knit.

The present document describes techniques associated with a textile-material model for vibroacoustic structural simulation. The techniques described herein provide a nontrivial methodology to test a textile and simplify its representation, which can enable prediction of acoustic performance (e.g., rub and buzz) of an electronic-speaker device having a textile mounted thereon. The textile is modeled as a textile-material model based on an elongation stiffness obtained from a time-temperature superposition curve of the textile, which is based on a dynamic mechanical analysis test of the textile in each of course and wale directions. The textile-material model is then applied to an assembly model of the electronic-speaker device to simulate a vibroacoustic response of the textile relative to the assembly model to predict a likelihood of rub and buzz.