# Knit-Pix2Pix: An Enhanced Pix2Pix Network for Weft-Knitted Fabric Texture Generation

## TL;DR

This paper introduces Knit-Pix2Pix, a new AI method for generating realistic weft-knitted fabric textures that better handle stretching and deformation.

## Contribution

The novel framework Knit-Pix2Pix integrates grid-guided attention and multi-scale components for deformation-aware fabric texture generation.

## Key findings

- Knit-Pix2Pix improves SSIM by 21.8% and PSNR by 20.9% over traditional methods.
- The framework reduces LPIPS by 24.3%, indicating better perceptual similarity.
- A dataset of 2000 fabric stretching image pairs was created and validated with simulations.

## Abstract

Texture mapping of weft-knitted fabrics plays a crucial role in virtual try-on and digital textile design due to its computational efficiency and real-time performance. However, traditional texture mapping techniques typically adapt pre-generated textures to deformed surfaces through geometric transformations. These methods overlook the complex variations in yarn length, thickness, and loop morphology during stretching, often resulting in visual distortions. To overcome these limitations, we propose Knit-Pix2Pix, a dedicated framework for generating realistic weft-knitted fabric textures directly from knitted unit mesh maps. These maps provide grid-based representations where each cell corresponds to a physical loop region, capturing its deformation state. Knit-Pix2Pix is an integrated architecture that combines a multi-scale feature extraction module, a grid-guided attention mechanism, and a multi-scale discriminator. Together, these components address the multi-scale and deformation-aware requirements of this task. To validate our approach, we constructed a dataset of over 2000 pairs of fabric stretching images and corresponding knitted unit mesh maps, with further testing using spring-mass fabric simulation. Experiments show that, compared with traditional texture mapping methods, SSIM increased by 21.8%, PSNR by 20.9%, and LPIPS decreased by 24.3%. This integrated approach provides a practical solution for meeting the requirements of digital textile design.