Neural Inverse Knitting: From Images to Manufacturing Instructions
This work addresses the challenge of mass customization in garment manufacturing by enabling automatic instruction generation from images, though it is incremental as it builds on existing machine learning techniques for a new application.
The paper tackles the problem of automatically generating machine knitting instructions from a single image of a desired physical product, proposing a method that learns to synthesize regular machine instructions from real images. The result includes a novel data mixing framework using synthetic images to augment a curated dataset, with empirical findings showing that making real images look more synthetic improves performance in this setup.
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.