Stitched Embeddings: A Unified Latent Space for 3D Garments and 2D Patterns

• URL: http://arxiv.org/abs/2607.00829v1
• Date: Wed, 01 Jul 2026 11:50:22 GMT
• Title: Stitched Embeddings: A Unified Latent Space for 3D Garments and 2D Patterns
• Abstract summary: Traditional tailoring relies on 2D sewing patterns, yet bridging these patterns to 3D geometry currently requires physical simulations.<n>We present Stitched Embeddings, the first simulation-free framework to unify 3D garment reconstruction and sewing pattern inference.
• Score: 35.36349252329493
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While garments are essential for realistic digital humans, their topological variety makes them much harder to model than parametric bodies. Traditional tailoring relies on 2D sewing patterns, yet bridging these patterns to 3D geometry currently requires physical simulations. We present Stitched Embeddings, the first simulation-free framework to unify 3D garment reconstruction and sewing pattern inference within a single bidirectional latent space. By leveraging the geometric priors of a pretrained 3D foundation model, our approach overcomes the data scarcity typically associated with high-quality garment modeling. We propose to use the BoxMesh as a critical intermediate representation to align 2D panels into 3D configurations without the computational overhead of a simulator. This architecture achieves state-of-the-art accuracy in pattern reconstruction while significantly improving efficiency. Furthermore, our differentiable pipeline enables novel applications, including pattern recovery from meshes and 3D editing from 2D patterns. Finally, this work provides a scalable link between neural 3D vision and the physical garment manufacturing pipeline. Project Page: https://andreus00.github.io/stitchedembeddings

Related papers

• Garment Particles: A 2D--3D Symmetric Garment Representation for Generation and Editing [53.22574954013334]
  Garment Particles is a 5D point-cloud representation that jointly encodes 2D sewing patterns and 3D geometry.<n>It supports intuitive generation from high-level inputs (text, images, sketches) and various editing operations on 2D sewing patterns and 3D geometries.<n>Our model also enables many garment editing scenarios, including garment, sewing pattern editing, point-cloud- and silhouette-conditioned garment generation.
  arXiv  Detail & Related papers  (2026-05-25T23:43:54Z)
• InverseDraping: Recovering Sewing Patterns from 3D Garment Surfaces via BoxMesh Bridging [17.48763627703864]
  We propose a two-stage framework that centers on a structured intermediate representation, BoxMesh.<n>BoxMesh encodes both garment-level geometry and panel-level structure in 3D.<n>We adopt autoregressive modeling to naturally handle the variable-length and structured nature of panel configurations and stitching relationships.
  arXiv  Detail & Related papers  (2026-04-03T06:19:12Z)
• SwiftTailor: Efficient 3D Garment Generation with Geometry Image Representation [14.56053056455189]
  We introduce SwiftTailor, a framework that unifies sewing-pattern reasoning and geometry-based mesh synthesis.<n>SwiftTailor achieves state-of-the-art accuracy and visual fidelity while significantly reducing inference time.<n>This work offers a scalable, interpretable, and high-performance solution for next-generation 3D garment generation.
  arXiv  Detail & Related papers  (2026-03-19T15:47:43Z)
• Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models [53.32092058519587]
  Stroke3D is a novel framework that directly generates rigged meshes from user inputs: 2D drawn strokes and a descriptive text prompt.<n>To the best of our knowledge, our work is the first to generate rigged 3D meshes conditioned on user-drawn 2D strokes.
  arXiv  Detail & Related papers  (2026-02-10T12:17:00Z)
• ReWeaver: Towards Simulation-Ready and Topology-Accurate Garment Reconstruction [32.919669263399534]
  ReWeaver is a novel framework for topology-accurate 3D garment and sewing pattern reconstruction from sparse multi-view RGB images.<n>We construct a large-scale dataset GCD-TS, comprising multi-view RGB images, 3D garment geometries, textured human body meshes and annotated sewing patterns.
  arXiv  Detail & Related papers  (2026-01-23T11:42:02Z)
• Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates [45.48311596587306]
  Reconstructing 3D clothed humans from images is fundamental to applications like virtual try-on, avatar creation, and mixed reality.<n>We present a novel method for high-fidelity 3D garment reconstruction from single images that bridges 2D and 3D representations.
  arXiv  Detail & Related papers  (2025-04-11T08:39:18Z)
• DiffusedWrinkles: A Diffusion-Based Model for Data-Driven Garment Animation [10.9550231281676]
  We present a data-driven method for learning to generate animations of 3D garments using a 2D image diffusion model.<n>Our approach is able to synthesize high-quality 3D animations for a wide variety of garments and body shapes.
  arXiv  Detail & Related papers  (2025-03-24T06:08:26Z)
• FAMOUS: High-Fidelity Monocular 3D Human Digitization Using View Synthesis [51.193297565630886]
  The challenge of accurately inferring texture remains, particularly in obscured areas such as the back of a person in frontal-view images. This limitation in texture prediction largely stems from the scarcity of large-scale and diverse 3D datasets. We propose leveraging extensive 2D fashion datasets to enhance both texture and shape prediction in 3D human digitization.
  arXiv  Detail & Related papers  (2024-10-13T01:25:05Z)
• SSR-2D: Semantic 3D Scene Reconstruction from 2D Images [54.46126685716471]
  In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without using any 3D annotations. The key idea of our approach is to design a trainable model that employs both incomplete 3D reconstructions and their corresponding source RGB-D images. Our method achieves the state-of-the-art performance of semantic scene completion on two large-scale benchmark datasets MatterPort3D and ScanNet.
  arXiv  Detail & Related papers  (2023-02-07T17:47:52Z)
• Structure-Preserving 3D Garment Modeling with Neural Sewing Machines [190.70647799442565]
  We propose a novel Neural Sewing Machine (NSM), a learning-based framework for structure-preserving 3D garment modeling. NSM is capable of representing 3D garments under diverse garment shapes and topologies, realistically reconstructing 3D garments from 2D images with the preserved structure, and accurately manipulating the 3D garment categories, shapes, and topologies.
  arXiv  Detail & Related papers  (2022-11-12T16:43:29Z)
• GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images [72.15855070133425]
  We introduce GET3D, a Generative model that directly generates Explicit Textured 3D meshes with complex topology, rich geometric details, and high-fidelity textures. GET3D is able to generate high-quality 3D textured meshes, ranging from cars, chairs, animals, motorbikes and human characters to buildings.
  arXiv  Detail & Related papers  (2022-09-22T17:16:19Z)

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.