Garments with finishing patterns created by laser and neural network
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 plurality of garments comprising:
a plurality of sample garments with lasered finishing patterns resulting from a plurality of sample laser input files;
a target garment comprising fabric panels made from a woven first material comprising a warp comprising dyed cotton yarn, wherein the fabric panels are sewn together using thread;
an outer surface of the target garment comprises a finishing pattern created by a laser based on a laser input file, wherein before lasering, a cross section of the warp of the target garment comprises a generally round shape,
after being exposed to the laser and a depth of material that has been removed, a cross section of the warp comprises a region with a flattened shape relative to the generally round shape before lasering; and
an existing garment made from a second material, wherein the first material comprises a different fabric characteristic from the second material, and the existing garment was created before the target garment was created,
the laser input file comprises digital data that is representative of a finishing pattern from the existing garment,
sample laser input files and images of sample garments with lasered finishing patterns that result from the sample laser input files are input to a generative adversarial network, and the sample laser input files comprise real laser input files,
fake laser input files are generated by a generative neural net of the adversarial network for images of sample garments with lasered finishing patterns,
a generator loss is determined based on the fake laser input files and real laser input files,
the real laser input files are input to a real discriminator and a fake discriminator of a generative adversarial network,
the fake laser input files are input to the fake discriminator of the generative adversarial network,
a discriminator loss is determined based on outputs of the real discriminator and fake discriminator,
a model is iteratively trained to obtain a final model based on outputs of the generator loss and discriminator loss, and
the laser input file for an image of the existing garment with the finishing pattern is generated by the final model.
2. The garments of claim 1 wherein the warp is ring dyed using an indigo dye,
based on the laser input file, selected amounts of material have been removed by the laser from the surface of the first material at different pixel locations of the target garment, and
for lighter pixel locations of the finishing pattern, a greater amount of the dyed cotton warp yarn is removed, revealing a greater width of an inner core of the dyed yarn, while for darker pixel locations of the finishing pattern, a lesser amount of the dyed cotton warp yarn is removed, revealing a lesser width of an inner core of the dyed yarn.
3. The garments of claim 1 wherein the finishing pattern created can extend across portions of the target garment where two or more fabric panels are joined together by thread by exposing these portions to the laser.
4. The garments of claim 1 wherein the first material comprises a weft comprising yarn that has not been dyed.
5. The garments of claim 1 wherein for the portions of the target garment exposed to the laser where the fabric panels are joined, the fabric panels are joined together using a thread comprising cotton.
6. The garments of claim 1 wherein the finishing pattern on the outer surface of the target garment was created by a single pass of a laser.
7. The garments of claim 1 wherein the finishing pattern on the outer surface of the target garment was created by multiple passes of a laser.
8. The garments of claim 1 wherein a target image of the finishing pattern is captured from the existing garment of the second material comprises using contrast limited adaptive histogram equalization image processing.
9. The garments of claim 1 wherein to create the finishing pattern on the outer surface of the target garment, different laser levels are obtained by varying an output of a 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.
10. The garments of claim 1 wherein the first material comprises a first surface texture characteristic which is different from a second surface texture characteristic of the second material.
11. The garments of claim 1 wherein the first material comprises a first dye characteristic which is different from a second dye characteristic of the second material.
12. The garments of claim 1 wherein the first material comprises a first base fabric color characteristic which is different from a second base fabric color characteristic of the second material.
13. The garments of claim 1 wherein the first material comprises a first yarn characteristic which is different from a second yarn characteristic of the second material.
14. The garments of claim 1 wherein the first material comprises a first yarn weight characteristic which is different from a second yarn weight characteristic of the second material.
15. The garments of claim 1 wherein the first material comprises a first yarn diameter characteristic which is different from a second yarn diameter characteristic of the second material.
16. The garments of claim 1 wherein the first material comprises a first yarn twist characteristic which is different from a second yarn twist characteristic of the second material.
17. The garments of claim 1 wherein the finishing pattern on the existing garment was not created by a laser.
18. The garments of claim 1 wherein the finishing pattern created by the laser on the target garment includes a wear pattern comprising at least one of combs or honeycombs, whiskers, stacks, or train tracks, or a combination.
19. A plurality of garments comprising:
a target garment comprising fabric panels made from a woven first material comprising a warp comprising dyed cotton yarn, wherein the fabric panels are sewn together using thread;
an outer surface of the target garment comprises a finishing pattern created by a laser based on a laser input file, wherein before lasering, a cross section of the warp of the target garment comprises a generally round shape,
after being exposed to the laser and a depth of material that has been removed, a cross section of the warp comprises a region with a flattened shape relative to the generally round shape before lasering; and
an existing garment made from a second material, wherein the first material comprises a different fabric characteristic from the second material, the existing garment with a finishing pattern existed before the target garment was created, and the finishing pattern on the existing garment was not created by a laser,
the laser input file comprises digital data that is representative of the finishing pattern from the existing garment,
a generative adversarial network comprises a generative neural net and a discriminative neural net,
a model is formed from the generative adversarial network, and
the laser input file for an image of the existing garment with the finishing pattern is generated by the model.
20. The garments of claim 19 wherein the garment comprises at least one of jeans, shirts, shorts, jackets, vests, or skirts.
21. The garments of claim 19 wherein the generative neural net generated fake laser input files and the fake laser input files are input to the discriminative neural net.