# 3D Virtual Garment Modeling from RGB Images

arXiv: https://arxiv.org/abs/1908.00114 · HTML: https://mlsanity.com/paper/1908.00114/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2019.

## Built on by (most cited first, 10 of 10)

- [Structure-Preserving 3D Garment Modeling with Neural Sewing Machines](https://mlsanity.com/paper/2211.06701/) (2022)
- [OutfitAnyone: Ultra-high Quality Virtual Try-On for Any Clothing and Any Person](https://mlsanity.com/paper/2407.16224/) (2024)
- [Robust 3D Garment Digitization from Monocular 2D Images for 3D Virtual Try-On Systems](https://mlsanity.com/paper/2111.15140/) (2021)
- [ClothCombo: Modeling Inter-Cloth Interaction for Draping Multi-Layered Clothes](https://mlsanity.com/paper/2304.03492/) (2023)
- [Cloth2Tex: A Customized Cloth Texture Generation Pipeline for 3D Virtual Try-On](https://mlsanity.com/paper/2308.04288/) (2023)
- [Per Garment Capture and Synthesis for Real-time Virtual Try-on](https://mlsanity.com/paper/2109.04654/) (2021)
- [High-Quality Animatable Dynamic Garment Reconstruction from Monocular Videos](https://mlsanity.com/paper/2311.01214/) (2023)
- [Smart Fashion: A Review of AI Applications in the Fashion & Apparel Industry](https://mlsanity.com/paper/2111.00905/) (2021)
- [DiffusedWrinkles: A Diffusion-Based Model for Data-Driven Garment Animation](https://mlsanity.com/paper/2503.18370/) (2025)
- [DeepIron: Predicting Unwarped Garment Texture from a Single Image](https://mlsanity.com/paper/2310.15447/) (2023)

## Abstract (arXiv)

We present a novel approach that constructs 3D virtual garment models from photos. Unlike previous methods that require photos of a garment on a human model or a mannequin, our approach can work with various states of the garment: on a model, on a mannequin, or on a flat surface. To construct a complete 3D virtual model, our approach only requires two images as input, one front view and one back view. We first apply a multi-task learning network called JFNet that jointly predicts fashion landmarks and parses a garment image into semantic parts. The predicted landmarks are used for estimating sizing information of the garment. Then, a template garment mesh is deformed based on the sizing information to generate the final 3D model. The semantic parts are utilized for extracting color textures from input images. The results of our approach can be used in various Virtual Reality and Mixed Reality applications.