Simulated garment dataset for virtual try-on

This repository contains the dataset used in the following papers:

Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On (CVPR 2021) [Project website] [Video]
Learning-Based Animation of Clothing for Virtual Try-On (Eurographics 2019) [Project website] [Video]

Dataset

The data is generated used a modified version of ARCSim and sequences from the CMU Motion Capture Database converted to SMPL format in SURREAL. Each simulated sequence is stored as a .pkl file that contains the following data:

Key	Description	Dimension
shapes	SMPL shape coefficients	[num_frames, 10]
poses	SMPL pose coefficients	[num_frames, 75]
vertices	Vertices of the simulated garment	[num_frames, num_vertices, 3]
faces	Faces of the garment	[num_faces, 3]
sequence	Sequence identifier
subject	Subject identifier
conf	ARCSim configuration

Extract meshes

Requirements: python3, numpy-1.21.3

To extract the simulated garment meshes as .obj run the following script:

python extract_meshes.py tshirt/simulations/tshirt_shape00_01_01.pkl

Citation

If you find this dataset useful please cite our work:

@article {santesteban2021garmentcollisions,
    journal = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    title = {{Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On}},
    author = {Santesteban, Igor and Thuerey, Nils and Otaduy, Miguel A and Casas, Dan},
    year = {2021}
}

@article {santesteban2019virtualtryon,
    journal = {Computer Graphics Forum (Proc. Eurographics)},
    title = {{Learning-Based Animation of Clothing for Virtual Try-On}},
    author = {Santesteban, Igor and Otaduy, Miguel A. and Casas, Dan},
    year = {2019},
    ISSN = {1467-8659},
    DOI = {10.1111/cgf.13643}
}

Simulated garment dataset for virtual try-on

Related tags

Overview

Simulated garment dataset for virtual try-on

Dataset

Extract meshes

Citation

Owner

ULMFiT for Genomic Sequence Data

SegNet-Basic with Keras

pytorch implementation for PointNet

Code for ICCV 2021 paper Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes using Scene Graphs

A torch implementation of "Pixel-Level Domain Transfer"

POPPY (Physical Optics Propagation in Python) is a Python package that simulates physical optical propagation including diffraction

High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI interface.

PyTorch code for the NAACL 2021 paper "Improving Generation and Evaluation of Visual Stories via Semantic Consistency"

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

Minimal implementation of PAWS (https://arxiv.org/abs/2104.13963) in TensorFlow.

DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

This is an implementation of Googles Yogi-Optimizer in Keras (tf.keras)

Includes PyTorch -> Keras model porting code for ConvNeXt family of models with fine-tuning and inference notebooks.

A very short and easy implementation of Quantile Regression DQN

Code for the paper "Can Active Learning Preemptively Mitigate Fairness Issues?" presented at RAI 2021.

PiRapGenerator - Make anyone rap the digits of pi

Official pytorch implementation of "Feature Stylization and Domain-aware Contrastive Loss for Domain Generalization" ACMMM 2021 (Oral)

Multi-Scale Aligned Distillation for Low-Resolution Detection (CVPR2021)

PyTorch implementation of Barlow Twins.

Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019