PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments

• URL: http://arxiv.org/abs/2606.24564v5
• Date: Thu, 02 Jul 2026 03:45:07 GMT
• Title: PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments
• Abstract summary: We present PatternGSL, a structured garment representation in the form of a template-free and learnable specification language.<n>We propose a vision-language framework that predicts PatternGSL specifications directly from a single image and decodes them into garments.
• Score: 52.50602518973252
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Reconstructing realistic, physically plausible garments from a single image remains a fundamental challenge. Template-free methods capture surface geometry but lack explicit sewing structure for simulation; while programmatic systems are simulation-ready but constrained by predefined templates. This reveals a fundamental representation gap between geometric reconstruction and structured garment construction. We present PatternGSL, a structured garment representation in the form of a template-free and learnable specification language that encodes complete sewing patterns, including panel boundaries, parameterized seams, and explicit stitch topology, in a compact and standardized form. PatternGSL preserves the physical rigor of pattern-based models while removing template dependence, elevating sewing structure as a first-class target for generative modeling. We further propose a vision-language framework that predicts PatternGSL specifications directly from a single image and decodes them into garments using lightweight deterministic validity handling, without optimization-based refinement or manual cleanup. In addition, we introduce PatternGSLData, the first large-scale image-to-GSL paired dataset comprising 300K samples with complete sewing pattern annotations, enabling supervised VLM training for structured garment reconstruction. Experiments demonstrate improved pattern accuracy over prior baselines, explicit sewing-structure recovery, reliable cloth simulation, and pattern-level editing through the same deterministic decoding pipeline. Code and data-processing scripts will be released at https://lagrangeli.github.io/PatternGSL/.

Related papers

• GarmentWeaver: Schema-Aware Structured Synthesis for Multimodal Sewing Patterns [3.5652803799913197]
  GarmentWeaver is a schema-aware framework for multimodal Sewing pattern generation.<n>It constructs compact hierarchical targets by activating garment-relevant structural branches.<n>Experiments show that GarmentWeaver produces more accurate and more executable sewing patterns than strong baselines.
  arXiv  Detail & Related papers  (2026-08-31T10:25:00Z)
• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• STEP-LLM: Generating CAD STEP Models from Natural Language with Large Language Models [16.811723701941546]
  We introduce novel preprocessing tailored for the graph-structured format of STEP.<n>We show consistent gains of our STEP-LLM in geometric fidelity over the Text2CAD baseline.
  arXiv  Detail & Related papers  (2026-01-19T01:10:49Z)
• GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling [35.49678134341859]
  GarmageNet is a generative framework that automates the creation of 2D sewing patterns.<n>Garmage is a novel garment representation that encodes each panel as a structured geometry image.<n>GarmageSet is a large-scale dataset comprising 14,801 professionally designed garments.
  arXiv  Detail & Related papers  (2025-04-02T08:37:32Z)
• ChatGarment: Garment Estimation, Generation and Editing via Large Language Models [79.46056192947924]
  ChatGarment is a novel approach that leverages large vision-language models (VLMs) to automate the estimation, generation, and editing of 3D garments.<n>It can estimate sewing patterns from in-the-wild images or sketches, generate them from text descriptions, and edit garments based on user instructions.
  arXiv  Detail & Related papers  (2024-12-23T18:59:28Z)
• PatternPaint: Practical Layout Pattern Generation Using Diffusion-Based Inpainting [4.9540362281086265]
  PatternPaint is a diffusion-based framework capable of generating legal patterns with limited design-rule-compliant training samples.<n>Our model is the only one that can generate legal patterns in complex 2D metal interconnect design rule settings.<n>As a result, we demonstrate a production-ready approach for layout pattern generation in developing new technology nodes.
  arXiv  Detail & Related papers  (2024-09-02T16:02:26Z)
• ChatPattern: Layout Pattern Customization via Natural Language [18.611898021267923]
  ChatPattern is a novel Large-Language-Model powered framework for flexible pattern customization. LLM agent can interpret natural language requirements and operate design tools to meet specified needs. generator excels in conditional layout generation, pattern modification, and memory-friendly patterns extension.
  arXiv  Detail & Related papers  (2024-03-15T09:15:22Z)
• ReshapeIT: Reliable Shape Interaction with Implicit Template for Anatomical Structure Reconstruction [59.971808117043366]
  ReShapeIT represents an anatomical structure with an implicit template field shared within the same category. It ensures the implicit template field generates valid templates by strengthening the constraint of the correspondence between the instance shape and the template shape. A template Interaction Module is introduced to reconstruct unseen shapes by interacting the valid template shapes with the instance-wise latent codes.
  arXiv  Detail & Related papers  (2023-12-11T07:09:32Z)
• CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model [55.321010757641524]
  We introduce CLIP4STR, a simple yet effective STR method built upon image and text encoders of CLIP.<n>We scale CLIP4STR in terms of the model size, pre-training data, and training data, achieving state-of-the-art performance on 13 STR benchmarks.
  arXiv  Detail & Related papers  (2023-05-23T12:51:20Z)
• Autoregressive Structured Prediction with Language Models [73.11519625765301]
  We describe an approach to model structures as sequences of actions in an autoregressive manner with PLMs. Our approach achieves the new state-of-the-art on all the structured prediction tasks we looked at.
  arXiv  Detail & Related papers  (2022-10-26T13:27:26Z)
• Learning Implicit Templates for Point-Based Clothed Human Modeling [33.6247548142638]
  We present FITE, a framework for modeling human avatars in clothing. Our framework first learns implicit surface templates representing the coarse clothing topology. We employ the templates to guide the generation of point sets which further capture pose-dependent clothing deformations such as wrinkles.
  arXiv  Detail & Related papers  (2022-07-14T14:25:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.