GUI for visualization and interactive editing of SMPL-family body models ie. SMPL, SMPL-X, MANO, FLAME.

Overview

Body Model Visualizer

Introduction

This is a simple Open3D-based GUI for SMPL-family body models. This GUI lets you play with the shape, expression, and pose parameters of SMPL, SMPL-X, MANO, FLAME body models. Features include:

  • Interactive editing of shape, expression, pose parameters
01_model_editing.mp4
  • Visualize body model joints and joint names
02_visualize_joints.mp4
  • Simple IK solver to match an input pose
03_simple_ik.mp4
  • Save edited model parameters
04_save_params.mp4
  • View controls
05_viewing.mp4
  • Lighting controls
06_lighting.mp4
  • Material settings
07_material.mp4

Even though there are existing Blender/Unity plugins for these models, our main audience here is researchers who would like to quickly edit/visualize body models without the need to install a graphics software.

Installation

Clone the repo and install the requirements (use python3.9).

pip install -r requirements.txt

Download the SMPL, SMPL-X, MANO, FLAME body models:

Copy downloaded files under data/body_models, this folder should look like:

data
└── body_models
    ├── flame
    │   ├── FLAME_FEMALE.pkl
    │   ├── FLAME_MALE.pkl
    │   ├── FLAME_NEUTRAL.pkl
    │   ├── flame_dynamic_embedding.npy
    │   └── flame_static_embedding.pkl
    ├── mano
    │   ├── MANO_LEFT.pkl
    │   └── MANO_RIGHT.pkl
    ├── smpl
    │   ├── SMPL_FEMALE.pkl
    │   ├── SMPL_MALE.pkl
    │   └── SMPL_NEUTRAL.pkl
    └── smplx
        ├── SMPLX_FEMALE.npz
        ├── SMPLX_MALE.npz
        └── SMPLX_NEUTRAL.npz

Finally, run:

python main.py

Guidelines

Saved model parameters

File > Save Model Params lets you save the edited body model parameters. Output is a pickled python dictionary with below keys:

dict_keys(['betas', 'expression', 'gender', 'body_model', 
           'joints', 'body_pose', 'global_orient'])
Comments
  • Follow the instructions, encounter segmentation error after running

    Follow the instructions, encounter segmentation error after running "python main.py"

    Hi, thanks for the great work. I set the environment as the instructions. But when I run the main.py file, it reports "Segmentation Fault" Here is the packages I've installed as following

    addict               2.4.0
    anyio                3.4.0
    argon2-cffi          21.3.0
    argon2-cffi-bindings 21.2.0
    attrs                21.2.0
    Babel                2.9.1
    backcall             0.2.0
    bleach               4.1.0
    certifi              2021.10.8
    cffi                 1.15.0
    charset-normalizer   2.0.9
    chumpy               0.70
    cycler               0.11.0
    debugpy              1.5.1
    decorator            5.1.0
    defusedxml           0.7.1
    deprecation          2.1.0
    entrypoints          0.3
    fonttools            4.28.5
    idna                 3.3
    ipdb                 0.13.9
    ipykernel            6.6.0
    ipython              7.30.1
    ipython-genutils     0.2.0
    ipywidgets           7.6.5
    jedi                 0.18.1
    Jinja2               3.0.3
    joblib               1.1.0
    json5                0.9.6
    jsonschema           4.3.2
    jupyter-client       7.1.0
    jupyter-core         4.9.1
    jupyter-packaging    0.11.1
    jupyter-server       1.13.1
    jupyterlab           3.2.5
    jupyterlab-pygments  0.1.2
    jupyterlab-server    2.10.1
    jupyterlab-widgets   1.0.2
    kiwisolver           1.3.2
    loguru               0.5.3
    MarkupSafe           2.0.1
    matplotlib           3.5.1
    matplotlib-inline    0.1.3
    mistune              0.8.4
    nbclassic            0.3.4
    nbclient             0.5.9
    nbconvert            6.3.0
    nbformat             5.1.3
    nest-asyncio         1.5.4
    notebook             6.4.6
    numpy                1.21.5
    open3d               0.14.1
    packaging            21.3
    pandas               1.3.5
    pandocfilters        1.5.0
    parso                0.8.3
    pexpect              4.8.0
    pickleshare          0.7.5
    Pillow               8.4.0
    pip                  21.2.4
    prometheus-client    0.12.0
    prompt-toolkit       3.0.24
    ptyprocess           0.7.0
    pycparser            2.21
    Pygments             2.10.0
    pyparsing            3.0.6
    pyrsistent           0.18.0
    python-dateutil      2.8.2
    pytz                 2021.3
    PyYAML               6.0
    pyzmq                22.3.0
    requests             2.26.0
    scikit-learn         1.0.2
    scipy                1.7.3
    Send2Trash           1.8.0
    setuptools           58.0.4
    six                  1.16.0
    smplx                0.1.28
    sniffio              1.2.0
    terminado            0.12.1
    testpath             0.5.0
    threadpoolctl        3.0.0
    toml                 0.10.2
    tomlkit              0.8.0
    torch                1.10.1
    tornado              6.1
    tqdm                 4.62.3
    traitlets            5.1.1
    typing_extensions    4.0.1
    urllib3              1.26.7
    wcwidth              0.2.5
    webencodings         0.5.1
    websocket-client     1.2.3
    wheel                0.37.0
    widgetsnbextension   3.5.2
    opened by AndyVerne 2
  • Installation error -- no matching distribution found for open3d

    Installation error -- no matching distribution found for open3d

    Running through the installation instructions yields an error in my WSL env:

    (test) [email protected]:~/body-model-visualizer# pip install -r requirements.txt
    Collecting ipdb==0.13.9
      Using cached ipdb-0.13.9.tar.gz (16 kB)
    Collecting joblib==1.1.0
      Using cached joblib-1.1.0-py2.py3-none-any.whl (306 kB)
    Collecting loguru==0.5.3
      Using cached loguru-0.5.3-py3-none-any.whl (57 kB)
    Collecting matplotlib==3.5.1
      Using cached matplotlib-3.5.1-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl (11.3 MB)
    Collecting numpy==1.21.5
      Using cached numpy-1.21.5-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (15.7 MB)
    ERROR: Could not find a version that satisfies the requirement open3d==0.14.1 (from -r requirements.txt (line 6)) (from versions: 0.10.0.0, 0.11.0, 0.11.1, 0.11.2,0.12.0, 0.13.0)
    ERROR: No matching distribution found for open3d==0.14.1 (from -r requirements.txt (line 6))
    (test) [email protected]:~/body-model-visualizer# 
    

    I can manually run pip install open3d, but that installs version 0.13.0. I assume this has something to do with my janky WSL setup, but I've been trying to debug it for a while and have not had any luck yet. I'm wondering if this is a bug in your repo's latest version?

    opened by domattioli 0
  • How to use saved .pkl parameters file?

    How to use saved .pkl parameters file?

    I have modified the smpl model and saved the pkl file,but i not load it in SMPL code. `def ready_arguments(fname_or_dict):

    if not isinstance(fname_or_dict, dict):
        #dd = pickle.load(open(fname_or_dict))
        dd = pickle.load(open(fname_or_dict,"rb"),encoding='iso-8859-1')
    else:
        dd = fname_or_dict
        
    backwards_compatibility_replacements(dd) `
    

    UnpicklingError invalid load key, '\x27'. File "/home/lrd/data/lrd/body-model-visualizer-filer/SMPL_python_v.1.1.0/smpl/smpl_webuser/serialization.py", line 81, in ready_arguments dd = pickle.load(open(fname_or_dict,"rb"),encoding='iso-8859-1') File "/home/lrd/data/lrd/body-model-visualizer-filer/SMPL_python_v.1.1.0/smpl/smpl_webuser/serialization.py", line 117, in load_model dd = ready_arguments(fname_or_dict) File "/home/lrd/data/lrd/body-model-visualizer-filer/SMPL_python_v.1.1.0/smpl/smpl_webuser/hello_world/hello_smpl.py", line 48, in <module> m = load_model( '/home/lrd/data/lrd/body-model-visualizer-filer/abc.pkl' )

    sometimes,it is other error. I don't konw how to use this saved parameters.

    opened by LRuid 0
  • Not able to load the saved parameters

    Not able to load the saved parameters

    Hi,

    I successfully run the GUI, change the joint rotation, and saved the parameters. However, I cannot load the .pkl file.

    Tried using

    import pickle
    
    file_name = '../subject2_Tpose.pkl'
    
    with open(file_name, 'rb') as f:  
        subject2_Tpose = pickle.load(f)  
        
    

    and

    import torch
    
    subject2_Tpose = torch.load(file_name)
    

    Both return the same error:

    UnpicklingError: A load persistent id instruction was encountered,
    but no persistent_load function was specified.
    

    The torch version is the same as where I ran the main.py. Any solution for this?

    opened by SizheAn 0
  • How can I visualize my own smpl model?

    How can I visualize my own smpl model?

    I already have some smpl pkl file and I want to use this application to view the model. It seems the codes can only modify based on the original smpl model. Thank you so mush if you could help with this!

    opened by kkpetra 0
Releases(v0.1)
Owner
Muhammed Kocabas
Muhammed Kocabas
Small binja plugin to import header file to types

binja-import-header (v1.0.0) Author: matteyeux Import header file to Binary Ninja types view Description: Binary Ninja plugin to import types from C h

matteyeux 15 Dec 10, 2022
Tidy data structures, summaries, and visualisations for missing data

naniar naniar provides principled, tidy ways to summarise, visualise, and manipulate missing data with minimal deviations from the workflows in ggplot

Nicholas Tierney 611 Dec 22, 2022
An automatic prover for tautologies in Metamath

completeness An automatic prover for tautologies in Metamath This program implements the constructive proof of the Completeness Theorem for propositio

Scott Fenton 2 Dec 15, 2021
✅ Today I Learn

Today I Learn EDA numpy_100ex numpy_0~10 airline_satisfaction_prediction BERT_naver_movie_classification NLP_prepare NLP_Tweet_Emotion_Recognition tex

Yeonghoo_Ahn 3 Dec 15, 2022
Generate the report for OCULTest.

Sample report generated in this function Usage example from utils.gen_report import generate_report if __name__ == '__main__': # def generate_rep

Philip Guo 1 Mar 10, 2022
Visualization of the World Religion Data dataset by Correlates of War Project.

World Religion Data Visualization Visualization of the World Religion Data dataset by Correlates of War Project. Mostly personal project to famirializ

Emile Bangma 1 Oct 15, 2022
Automate the case review on legal case documents and find the most critical cases using network analysis

Automation on Legal Court Cases Review This project is to automate the case review on legal case documents and find the most critical cases using netw

Yi Yin 7 Dec 28, 2022
Design your own matplotlib stylefile interactively

Tired of playing with font sizes and other matplotlib parameters every time you start a new project or write a new plotting function? Want all you plots have the same style? Use matplotlib configurat

yobi byte 207 Dec 08, 2022
Matplotlib colormaps from the yt project !

cmyt Matplotlib colormaps from the yt project ! Colormaps overview The following colormaps, as well as their respective reversed (*_r) versions are av

The yt project 5 Sep 16, 2022
A concise grammar of interactive graphics, built on Vega.

Vega-Lite Vega-Lite provides a higher-level grammar for visual analysis that generates complete Vega specifications. You can find more details, docume

Vega 4k Jan 08, 2023
A curated list of awesome Dash (plotly) resources

Awesome Dash A curated list of awesome Dash (plotly) resources Dash is a productive Python framework for building web applications. Written on top of

Luke Singham 1.7k Jan 07, 2023
Visualization Library

CamViz Overview // Installation // Demos // License Overview CamViz is a visualization library developed by the TRI-ML team with the goal of providing

Toyota Research Institute - Machine Learning 67 Nov 24, 2022
A grammar of graphics for Python

plotnine Latest Release License DOI Build Status Coverage Documentation plotnine is an implementation of a grammar of graphics in Python, it is based

Hassan Kibirige 3.3k Jan 01, 2023
Lime: Explaining the predictions of any machine learning classifier

lime This project is about explaining what machine learning classifiers (or models) are doing. At the moment, we support explaining individual predict

Marco Tulio Correia Ribeiro 10.3k Dec 29, 2022
A Python package that provides evaluation and visualization tools for the DexYCB dataset

DexYCB Toolkit DexYCB Toolkit is a Python package that provides evaluation and visualization tools for the DexYCB dataset. The dataset and results wer

NVIDIA Research Projects 107 Dec 26, 2022
Automatically Visualize any dataset, any size with a single line of code. Created by Ram Seshadri. Collaborators Welcome. Permission Granted upon Request.

AutoViz Automatically Visualize any dataset, any size with a single line of code. AutoViz performs automatic visualization of any dataset with one lin

AutoViz and Auto_ViML 1k Jan 02, 2023
FURY - A software library for scientific visualization in Python

Free Unified Rendering in Python A software library for scientific visualization in Python. General Information • Key Features • Installation • How to

169 Dec 21, 2022
Project coded in Python using Pandas to look at changes in chase% for batters facing a pitcher first time through the order vs. thrid time

Project coded in Python using Pandas to look at changes in chase% for batters facing a pitcher first time through the order vs. thrid time

Jason Kraynak 1 Jan 07, 2022
Editor and Presenter for Manim Generated Content.

Editor and Presenter for Manim Generated Content. Take a look at the Working Example. More information can be found on the documentation. These Browse

Manim Community 149 Dec 29, 2022
Gaphas is the diagramming widget library for Python.

Gaphas Gaphas is the diagramming widget library for Python. Gaphas is a library that provides the user interface component (widget) for drawing diagra

Gaphor 144 Dec 14, 2022