GarmentImage: Raster Encoding of Garment Sewing Patterns with Diverse Topologies
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909602076950528 |
|---|---|
| author | Tatsukawa, Yuki Qi, Anran Shen, I-Chao Igarashi, Takeo |
| author_facet | Tatsukawa, Yuki Qi, Anran Shen, I-Chao Igarashi, Takeo |
| contents | Garment sewing patterns are the design language behind clothing, yet their current vector-based digital representations weren't built with machine learning in mind. Vector-based representation encodes a sewing pattern as a discrete set of panels, each defined as a sequence of lines and curves, stitching information between panels and the placement of each panel around a body. However, this representation causes two major challenges for neural networks: discontinuity in latent space between patterns with different topologies and limited generalization to garments with unseen topologies in the training data. In this work, we introduce GarmentImage, a unified raster-based sewing pattern representation. GarmentImage encodes a garment sewing pattern's geometry, topology and placement into multi-channel regular grids. Machine learning models trained on GarmentImage achieve seamless transitions between patterns with different topologies and show better generalization capabilities compared to models trained on vector-based representation. We demonstrate the effectiveness of GarmentImage across three applications: pattern exploration in latent space, text-based pattern editing, and image-to-pattern prediction. The results show that GarmentImage achieves superior performance on these applications using only simple convolutional networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_02592 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GarmentImage: Raster Encoding of Garment Sewing Patterns with Diverse Topologies Tatsukawa, Yuki Qi, Anran Shen, I-Chao Igarashi, Takeo Graphics Garment sewing patterns are the design language behind clothing, yet their current vector-based digital representations weren't built with machine learning in mind. Vector-based representation encodes a sewing pattern as a discrete set of panels, each defined as a sequence of lines and curves, stitching information between panels and the placement of each panel around a body. However, this representation causes two major challenges for neural networks: discontinuity in latent space between patterns with different topologies and limited generalization to garments with unseen topologies in the training data. In this work, we introduce GarmentImage, a unified raster-based sewing pattern representation. GarmentImage encodes a garment sewing pattern's geometry, topology and placement into multi-channel regular grids. Machine learning models trained on GarmentImage achieve seamless transitions between patterns with different topologies and show better generalization capabilities compared to models trained on vector-based representation. We demonstrate the effectiveness of GarmentImage across three applications: pattern exploration in latent space, text-based pattern editing, and image-to-pattern prediction. The results show that GarmentImage achieves superior performance on these applications using only simple convolutional networks. |
| title | GarmentImage: Raster Encoding of Garment Sewing Patterns with Diverse Topologies |
| topic | Graphics |
| url | https://arxiv.org/abs/2505.02592 |