Learning a shared shape space for multimodal garment design

  title={Learning a shared shape space for multimodal garment design},
  author={Tuanfeng Y. Wang and Duygu Ceylan and Jovan Popovi{\'c} and Niloy Jyoti Mitra},
  journal={ACM Transactions on Graphics (TOG)},
  pages={1 - 13}
Designing real and virtual garments is becoming extremely demanding with rapidly changing fashion trends and increasing need for synthesizing realisticly dressed digital humans for various applications. This necessitates creating simple and effective workflows to facilitate authoring sewing patterns customized to garment and target body shapes to achieve desired looks. Traditional workflow involves a trial-and-error procedure wherein a mannequin is draped to judge the resultant folds and the… 

Wrinkle synthesis for cloth mesh with hermite radial basis functions

A new geometric method for adding believable wrinkles to existing virtual clothing that takes advantage of angles between gradients of adjacent HRBF scalar fields to trace spatially and temporally coherent wrinkle curves on a cloth mesh.

Fashion Transfer: Dressing 3D Characters from Stylized Fashion Sketches

Key to the method is the strategy to extract both shape and repetitive patterns of folds from the 2D input, which can be used to dress a variety of characters of different morphologies, from virtual humans to cartoon‐style characters.

Generating Datasets of 3D Garments with Sewing Patterns

This work has created the first large-scale synthetic dataset of 3D garment models with their sewing patterns and created the automatic generation pipeline to produce garment 3D models with little-to-none manual intervention.

Learning an intrinsic garment space for interactive authoring of garment animation

This work presents a deep-learning-based approach for semi-automatic authoring of garment animation, wherein the user provides the desired garment shape in a selection of keyframes, while the system infers a latent representation for its motion-independent intrinsic parameters.

Dynamic neural garments

This work proposes dynamic neural garments to synthesize plausible dynamic garment appearance from a desired viewpoint, and generates a coarse garment proxy sequence, learns deep dynamic features attached to this template, and neurally renders the features to produce appearance changes such as folds, wrinkles, and silhouettes.

GAN-Based Garment Generation Using Sewing Pattern Images

The generative model has high reconstruction accuracy and can provide rich variations of virtual garments, and a large garment appearance dataset is provided for use in garment reconstruction, garment capturing, and other applications.

Deep Detail Enhancement for Any Garment

This paper introduces a patch‐based formulation, that produces high‐resolution details by matching a Gram matrix based style loss, to hallucinate geometric details (i.e., wrinkle density and shape), and shows how to enhance, in a data‐driven manner, rich yet plausible details starting from a coarse garment geometry.

3D Custom Fit Garment Design with Body Movement

The method is able to create garments for people who fall far outside the range of standard sizes, like this model, whose height is 125 cm.

Learning Cloth Dynamics: 3D+Texture Garment Reconstruction Benchmark

A large-scale dataset of animated garments with variable topology and type, called CLOTH3D++, containing RGBA video sequences paired with its corresponding 3D data, and a competition to develop the best method to perform 3D garment reconstruction in a sequence from 3D-to-3D garments.

3D Shape-Adapted Garment Generation with Sketches

This paper presents a data-driven approach wherein 3D garments are directly generated from sketches combining given body shape parameters, an encoder-decoder architecture, and shows the effect of body shape and sketch on the generated garment.



Foldsketch: enriching garments with physically reproducible folds

FoldSketch is presented, a new system that supports simple and intuitive fold and pleat design that reliably converges to a desired garment geometry and corresponding patterns and drape, and works well with different physical simulators.

Physics-driven pattern adjustment for direct 3D garment editing

A new framework is proposed that allows designers to directly apply the changes they envision in 3D space; and creates the 2D patterns that replicate this envisioned target geometry when lifted into 3D via a physical draping simulation.

DeepGarment : 3D Garment Shape Estimation from a Single Image

This work illustrates that this technique is able to recover the global shape of dynamic 3D garments from a single image under varying factors such as challenging human poses, self occlusions, various camera poses and lighting conditions, at interactive rates.

Sketching garments for virtual characters

A method for simply and interactively creating basic garments for dressing virtual characters in applications like video games, integrated in an interactive system in which the user sketches the garment over the 3D model of the character.

Design preserving garment transfer

This work reformulates the criteria used in professional pattern-grading as a set of geometric requirements, respectively expressing shape or design preservation, proportionality, and fit, and proposes a fully automatic garment transfer algorithm which satisfies all of these criteria while ensuring the physical plausibility of the result.

Garment modeling with a depth camera

This work studies the modeling of real garments and develops a system that is intuitive to use even for novice users, including garment component detectors and design attribute classifiers learned from a manually labeled garment image database.

Context-aware garment modeling from sketches

Garment Modeling from a Single Image

This work designs an all-pose garment outline interpretation, and a shading-based detail modeling algorithm that achieves similar result quality as prior methods from just a single image, significantly improving the flexibility of garment modeling.

Sensitive couture for interactive garment modeling and editing

A novel interactive tool for garment design that enables, for the first time, interactive bidirectional editing between 2D patterns and 3D high-fidelity simulated draped forms, enabling rapid prototyping and an intuitive understanding of complex drape form.

Sketching Folds

This work presents the first sketch-based modeling method for developable surfaces with pre-designed folds, such as garments or leather products, implemented in a multiview sketching system where the user can sketch the contours of internal folds in addition to the usual silhouettes, borders, and seam lines.