# SewFusion: Tailored Generation of Topology and Panel-Level Geometry for Sewing Patterns

arXiv: https://arxiv.org/abs/2609.23548 · HTML: https://mlsanity.com/paper/2609.23548/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 20 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025)
- [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025)
- [Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation](https://mlsanity.com/paper/2602.02214/) (2026)
- [Learning a Shared Shape Space for Multimodal Garment Design](https://mlsanity.com/paper/1806.11335/) (2018)
- [End-to-End Training for Autoregressive Video Diffusion via Self-Resampling](https://mlsanity.com/paper/2512.15702/) (2025)
- [DressCode: Autoregressively Sewing and Generating Garments from Text Guidance](https://mlsanity.com/paper/2401.16465/) (2024)
- [GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion](https://mlsanity.com/paper/2104.05177/) (2021)
- [DrapeNet: Garment Generation and Self-Supervised Draping](https://mlsanity.com/paper/2211.11277/) (2022)
- [DiffAvatar: Simulation-Ready Garment Optimization with Differentiable Simulation](https://mlsanity.com/paper/2311.12194/) (2023)
- [Registering Explicit to Implicit: Towards High-Fidelity Garment mesh Reconstruction from Single Images](https://mlsanity.com/paper/2203.15007/) (2022)
- [Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction](https://mlsanity.com/paper/2108.08478/) (2021)
- [ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns](https://mlsanity.com/paper/2305.14100/) (2023)
- [REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videos](https://mlsanity.com/paper/2305.14236/) (2023)
- [Garment Recovery with Shape and Deformation Priors](https://mlsanity.com/paper/2311.10356/) (2023)
- [Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physics](https://mlsanity.com/paper/2502.03449/) (2025)
- [Multimodal Latent Diffusion Model for Complex Sewing Pattern Generation](https://mlsanity.com/paper/2412.14453/) (2024)
- [Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates](https://mlsanity.com/paper/2504.08353/) (2025)
- [GarmentImage: Raster Encoding of Garment Sewing Patterns with Diverse Topologies](https://mlsanity.com/paper/2505.02592/) (2025)
- [Reconstruction of Manipulated Garment with Guided Deformation Prior](https://mlsanity.com/paper/2405.10934/) (2024)
- [GarmentDiffusion: 3D Garment Sewing Pattern Generation with Multimodal Diffusion Transformers](https://mlsanity.com/paper/2504.21476/) (2025)
- [Garment Particles: A 2D--3D Symmetric Garment Representation for Generation and Editing](https://mlsanity.com/paper/2605.26391/) (2026)
- [VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation](https://mlsanity.com/paper/2605.30317/) (2026)
- [PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments](https://mlsanity.com/paper/2606.24564/) (2026)
- [Learning-based Seam Correspondence Reconstruction in Sewing Patterns](https://mlsanity.com/paper/2607.21213/) (2026)

## Abstract (arXiv)

Generating sewing patterns from images and text requires modeling a heterogeneous representation composed of discrete topology and continuous geometry. Existing methods mainly follow two paradigms: diffusion-based methods enable holistic geometry generation by converting the entire pattern into a continuous representation, but weaken discrete topology modeling; in contrast, autoregressive methods preserve discrete topology through next-token prediction, but tie continuous geometry regression to token-level hidden states with limited panel-level context. To bridge this gap, we propose SewFusion, a unified autoregressive framework that adopts tailored generation mechanisms for discrete topology and panel-level continuous geometry, using next-token prediction for the former and flow matching for the latter. To support panel-level continuous geometry generation, we introduce a Panel Geometry VAE that learns a fixed-size latent space for variable-length panel geometry, together with Panel Geometry Flow for latent generation. We further propose Panel-Forcing to reduce the training--inference mismatch in topology context and improve robustness to topology prediction errors. Extensive experiments on SewFactory and GCD-MM demonstrate that SewFusion consistently outperforms previous state-of-the-art methods across various settings, achieving +6.36% Panel Accuracy, +11.30% Stitch Accuracy, and -1.90 Vertex L2 error in the image-text-based generation setting.