Using Neural Networks in Creating Apparel Designs
Software and lasers are used in finishing apparel to produce a desired wear pattern or other design. A technique includes using machine learning to create or extract a laser input file for wear pattern from an existing garment. Machine learning can be by a generative adversarial network, having generative and discriminative neural nets. The generative adversarial network is trained and then used to create a model. This model is used generate the laser input file from an image of the existing garment with the finishing pattern. With this laser input file, a laser can re-create the wear pattern from the existing garment onto a new garment.
1 . A method comprising:
assembling a garment made from fabric panels of a woven first material comprising a warp comprising indigo ring-dyed cotton yarn, wherein the fabric panels are sewn together using thread;
using a model formed through a machine learning comprising a generative adversarial network, creating a laser input file that is representative of a finishing pattern from an existing garment made from a second material, wherein the first material comprises a different fabric characteristic from the second material; and
using a laser to create a finishing pattern on an outer surface of the garment based on the laser input file created by the model, wherein based on the laser input file, the laser removes selected amounts of material from the surface of the first material at different pixel locations of the garment,
for lighter pixel locations of the finishing pattern, a greater amount of the indigo ring-dyed cotton warp yarn is removed, while for darker pixel locations of the finishing pattern, a lesser amount of the indigo ring-dyed cotton warp yarn is removed, and
the finishing pattern created can extend across portions of the garment where two or more fabric panels are joined together by the threads by exposing these portions to the laser.
2 . The method of claim 1 wherein the generative adversarial network comprises a generative neural net and a discriminative neural net, and the generative adversarial network is trained by
providing as input a plurality of laser input files and images of garments burned with the laser input files, and
the generative neural net generating laser input files candidates for the discriminative neural net to determine whether the candidates appear real or fake.
3 . The method of claim 1 wherein the first material comprises a denim and the second material comprises a denim.
4 . The method of claim 1 wherein the garment comprises at least one of jeans, shirts, shorts, jackets, vests, or skirts.
5 . The method of claim 1 wherein the garment and the existing garment are of the same type of garment.
6 . The method of claim 1 wherein the finishing pattern created by the laser on the garment includes wear patterns comprising at least one of combs or honeycombs, whiskers, stacks, or train tracks, or a combination.
7 . A method comprising:
providing an assembled garment made from fabric panels of a woven first material comprising a warp comprising indigo ring-dyed cotton yarn, wherein the fabric panels are sewn together using thread;
providing a laser input file that is representative of a finishing pattern from an existing garment made from a second material, wherein the finishing pattern on the existing garment was not created by a laser, and the laser input file was obtained by
training a generative adversarial network comprising a generative neural net and a discriminative neural net, and
forming a model from the generative adversarial network, wherein the model generates the laser input file for an image of the existing garment with the finishing pattern; and
using a laser to create a finishing pattern on an outer surface of the assembled garment based on the laser input file, wherein based on the laser input file, the laser removes selected amounts of material from the surface of the first material at different pixel locations of the assembled garment,
for lighter pixel locations of the finishing pattern, a greater amount of the indigo ring-dyed cotton warp yarn is removed, while for darker pixel locations of the finishing pattern, a lesser amount of the indigo ring-dyed cotton warp yarn is removed, and
the finishing pattern created can extend across portions of the assembled garment where two or more fabric panels are joined together by the threads by exposing these portions to the laser.
8 . The method of claim 7 wherein the first material comprises a denim and the second material comprises a denim, the garment and the existing garment comprise a jean, and the finishing pattern created by the laser on the garment includes wear patterns comprising at least one of combs or honeycombs, whiskers, stacks, or train tracks, or a combination.
9 . A method comprising:
assembling a jean made from fabric panels of a woven first denim material comprising a warp comprising indigo ring-dyed cotton yarn, wherein the fabric panels are sewn together using thread;
creating a laser input file that is representative of a finishing pattern from an existing jean made from a second denim material, wherein the first denim material comprises a different fabric characteristic from the second denim material, and the creating the laser input file comprises
using machine learning to form a model, wherein the model generates the laser input file for an image of the existing garment with the finishing pattern; and
using a laser to create a finishing pattern on an outer surface of the jean based on the laser input file, wherein based on the laser input file, the laser removes selected amounts of material from the surface of the first material at different pixel locations of the jean,
for lighter pixel locations of the finishing pattern, a greater amount of the indigo ring-dyed cotton warp yarn is removed, while for darker pixel locations of the finishing pattern, a lesser amount of the indigo ring-dyed cotton warp yarn is removed, and
the finishing pattern created can extend across portions of the jean where two or more fabric panels are joined together by the threads by exposing these portions to the laser.
10 . The method of claim 9 wherein the first denim material comprises a weft comprising yarn that has not been indigo dyed.
11 . The method of claim 9 wherein for the portions of the jean exposed to the laser where the fabric panels are joined, the fabric panels are joined together using a thread comprising cotton.
12 . The method of claim 9 the determining values for the laser input file comprises:
selecting a dark reference in the target image of the finishing pattern from the existing jean of the second denim material;
for each pixel in the target image, calculating a difference value between a pixel value and the dark reference; and
storing each difference value in the laser input file, wherein the laser input file comprises a reverse image compared to target image.
13 . The method of claim 9 wherein the using a laser to create a finishing pattern on an outer surface of the jean comprises a single pass of the laser.
14 . The method of claim 9 wherein the using a laser to create a finishing pattern on an outer surface of the jean comprises multiple passes of the laser.
15 . The method of claim 9 wherein when using a laser to create a finishing pattern, different laser levels are obtained by varying an output of the laser beam by altering a characteristic of the laser comprising at least one of a frequency, period, pulse width, power, duty cycle, or burning speed.
16 . The method of claim 9 wherein the first denim material comprises a first surface texture characteristic which is different from a second surface texture characteristic of the second denim material.
17 . The method of claim 9 wherein the first denim material comprises a first dye characteristic which is different from a second dye characteristic of the second denim material.
18 . The method of claim 9 wherein the first denim material comprises a first base fabric color characteristic which is different from a second base fabric color characteristic of the second denim material.
19 . The method of claim 9 wherein the first denim material comprises a first yarn characteristic which is different from a second yarn characteristic of the second denim material.
20 . The method of claim 9 wherein the first denim material comprises a first yarn weight characteristic which is different from a second yarn weight characteristic of the second denim material.
21 . The method of claim 9 wherein the first denim material comprises a first yarn diameter characteristic which is different from a second yarn diameter characteristic of the second denim material.
22 . The method of claim 9 wherein the first denim material comprises a first yarn twist characteristic which is different from a second yarn twist characteristic of the second denim material.