Neural inverse knitting: From images to manufacturing instructions
Motivated by the recent potential of mass customization brought by whole-garment knitting machines, we introduce the new problem of automatic machine instruction generation using a single image of the desired physical product, which we apply to machine knitting. We propose to tackle this problem by...
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
Proceedings of Machine Learning Research
2021
|
Online Access: | https://hdl.handle.net/1721.1/129718 |
_version_ | 1811085414955483136 |
---|---|
author | Kaspar, Alexandre Oh, Taehyun Makatura, Liane Kellnhofer, Petr Matusik, Wojciech |
author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Kaspar, Alexandre Oh, Taehyun Makatura, Liane Kellnhofer, Petr Matusik, Wojciech |
author_sort | Kaspar, Alexandre |
collection | MIT |
description | Motivated by the recent potential of mass customization brought by whole-garment knitting machines, we introduce the new problem of automatic machine instruction generation using a single image of the desired physical product, which we apply to machine knitting. We propose to tackle this problem by directly learning to synthesize regular machine instructions from real images. We create a cured dataset of real samples with their instruction counterpart and propose to use synthetic images to augment it in a novel way. We theoretically motivate our data mixing framework and show empirical results suggesting that making real images look more synthetic is beneficial in our problem setup. |
first_indexed | 2024-09-23T13:09:13Z |
format | Article |
id | mit-1721.1/129718 |
institution | Massachusetts Institute of Technology |
language | English |
last_indexed | 2024-09-23T13:09:13Z |
publishDate | 2021 |
publisher | Proceedings of Machine Learning Research |
record_format | dspace |
spelling | mit-1721.1/1297182022-10-01T13:23:31Z Neural inverse knitting: From images to manufacturing instructions Kaspar, Alexandre Oh, Taehyun Makatura, Liane Kellnhofer, Petr Matusik, Wojciech Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Motivated by the recent potential of mass customization brought by whole-garment knitting machines, we introduce the new problem of automatic machine instruction generation using a single image of the desired physical product, which we apply to machine knitting. We propose to tackle this problem by directly learning to synthesize regular machine instructions from real images. We create a cured dataset of real samples with their instruction counterpart and propose to use synthetic images to augment it in a novel way. We theoretically motivate our data mixing framework and show empirical results suggesting that making real images look more synthetic is beneficial in our problem setup. 2021-02-08T23:09:06Z 2021-02-08T23:09:06Z 2019 2021-02-05T18:42:08Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/129718 Kaspar, Alexandre et al. "Neural inverse knitting: From images to manufacturing instructions." ICML 2019: 36th International Conference on Machine Learning, June, 2019, Long Beach, California, Proceedings of Machine Learning Research, 2019. © 2019 The Authors en http://proceedings.mlr.press/v97/kaspar19a.html ICML 2019: 36th International Conference on Machine Learning Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Proceedings of Machine Learning Research arXiv |
spellingShingle | Kaspar, Alexandre Oh, Taehyun Makatura, Liane Kellnhofer, Petr Matusik, Wojciech Neural inverse knitting: From images to manufacturing instructions |
title | Neural inverse knitting: From images to manufacturing instructions |
title_full | Neural inverse knitting: From images to manufacturing instructions |
title_fullStr | Neural inverse knitting: From images to manufacturing instructions |
title_full_unstemmed | Neural inverse knitting: From images to manufacturing instructions |
title_short | Neural inverse knitting: From images to manufacturing instructions |
title_sort | neural inverse knitting from images to manufacturing instructions |
url | https://hdl.handle.net/1721.1/129718 |
work_keys_str_mv | AT kasparalexandre neuralinverseknittingfromimagestomanufacturinginstructions AT ohtaehyun neuralinverseknittingfromimagestomanufacturinginstructions AT makaturaliane neuralinverseknittingfromimagestomanufacturinginstructions AT kellnhoferpetr neuralinverseknittingfromimagestomanufacturinginstructions AT matusikwojciech neuralinverseknittingfromimagestomanufacturinginstructions |