pictorial-maps-3d-humans

https://github.com/narrat3d/pictorial-maps-3d-humans

Science Score: 65.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
✓
DOI references
Found 3 DOI reference(s) in README
○
Academic publication links
○
Academic email domains
✓
Institutional organization owner
Organization narrat3d has institutional domain (narrat3d.ethz.ch)
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (8.7%) to scientific vocabulary

Last synced: 6 months ago · JSON representation ·

Repository

Basic Info

Host: GitHub
Owner: narrat3d
License: mit
Language: JavaScript
Default Branch: main
Homepage: http://narrat3d.ethz.ch/3d-humans-from-pictorial-maps/
Size: 16.3 MB

Statistics

Stars: 1
Watchers: 0
Forks: 0
Open Issues: 0
Releases: 0

Created about 2 years ago · Last pushed almost 2 years ago

Metadata Files

Readme License Citation

Inferring 3D human figures from pictorial maps

This is code for the article Inferring Implicit 3D Representations from Human Figures on Pictorial Maps. Visit the project website for more information or find further READMEs in the subfolders.

Figure_on_map

Git configuration

Use 'git submodule update --init --recursive --force --remote' to check out the submodules.
Use 'git submodule update --remote --merge' to update the submodules once they are checked-out.

Installation (on Windows)

Install Python 3.7 and 3.8
Install CUDA Toolkit 10.0 and 11.2 and corresponding cuDNNs
Install Blender 2.93 and 3.1, only needed for creating training data and converting 3D meshes
Run tf1installation.bat (needed for 3D pose estimation) after editing the PYTHONDIR variable
Run tf2installation.bat (needed for data preparation, 3D body part inference, uv coordinates prediction) after editing the PYTHONDIR variable
Run ptinstallation.bat (needed for texture inpainting) after editing the PYTHONDIR variable

Inference with pre-trained models

Download our test data and the pre-trained models from the project website.
Run 3dreconstruction.bat after editing the REPOSITORYFOLDER, MODELFOLDER, FIGURETARFILE variables.
Compare your results with ours from the project website.

Training the networks

Download our training and validation data from the project website.
See README.md in each sub-network folder for more information

Creation of training and validation data

Download the SMPL-X plugin for Blender, poses from AGORA, textures from SURREAL and Multi-Garment
Run 0datapreparation/bodypartsplitter_batch.py
Run 0datapreparation/objtosdf_batch.py

Creation of test data

Import our extracted test data from the project website to supervise.ly with the Supervisely plugin.
Upload your own images to the imported project and annotate your own pictorial figures with supervise.ly.
Export the annotations as .json + images and download the .tar file.

Notes

Optionally enable long folder paths (> 256 characters) if you get problems with the 3D pose estimation models

Eating

Citation

Please cite the following article when using this code:

@article{schnuerer2024inferring, author = {Raimund Schnürer, A. Cengiz Öztireli, Magnus Heitzler, René Sieber and Lorenz Hurni}, title = {Inferring implicit 3D representations from human figures on pictorial maps}, journal = {Cartography and Geographic Information Science}, volume = {51}, number = {1}, pages = {97-113}, year = {2024}, doi = {10.1080/15230406.2023.2224063} }

Owner

Name: narrat3d
Login: narrat3d
Kind: organization
Email: schnuerer@ethz.ch

Website: http://narrat3d.ethz.ch/
Repositories: 1
Profile: https://github.com/narrat3d

Codebase for the doctoral project "Storytelling with Animated Interactive Objects in Real-time 3D Maps"

Citation (CITATION.cff)

cff-version: 1.2.0
message: Please cite the following works when using this code.
preferred-citation:
  authors:
    - family-names: Schnürer
      given-names: Raimund
    - family-names: Öztireli
      given-names: A. Cengiz
    - family-names: Heitzler
      given-names: Magnus
    - family-names: Sieber
      given-names: René
    - family-names: Hurni
      given-names: Lorenz
  doi: 10.1080/15230406.2023.2224063
  identifiers:
    - type: doi
      value: 10.1080/15230406.2023.2224063
    - type: url
      value: https://doi.org/10.1080/15230406.2023.2224063
    - type: other
      value: urn:issn:1523-0406
  title: Inferring implicit 3D representations from human figures on pictorial maps
  type: article
  url: https://doi.org/10.1080/15230406.2023.2224063
  date-published: 2023-06-26
  year: 2024
  month: 2
  issn: 1523-0406
  issue: '1'
  journal: Cartography and Geographic Information Science
  languages:
    - en
  start: '97'
  end: '113'
  volume: '51'

GitHub Events

Total

Last Year

Dependencies

5b_virtual_globe/ThirdParty/codemirror-4.6/bower.json bower

5b_virtual_globe/ThirdParty/codemirror-4.6/package.json npm

node-static 0.6.0 development
phantomjs 1.9.2-5 development

5b_virtual_globe/ThirdParty/dojo-release-1.10.4/dijit/package.json npm

dojo 1.10.4

5b_virtual_globe/ThirdParty/dojo-release-1.10.4/dojo/package.json npm

5b_virtual_globe/package.json npm

almond ^0.3.3 development
aws-sdk ^2.18.0 development
bluebird ^3.4.6 development
compressible ^2.0.9 development
compression ^1.6.2 development
electron ^1.6.1 development
event-stream ^3.3.4 development
express ^4.15.0 development
globby ^6.1.0 development
glsl-strip-comments ^1.0.0 development
gulp ^3.9.1 development
gulp-insert ^0.5.0 development
gulp-jshint ^2.0.4 development
gulp-rename ^1.2.2 development
gulp-replace ^0.5.4 development
gulp-tap ^0.4.1 development
gulp-zip ^4.0.0 development
jasmine-core ^2.5.2 development
jsdoc ^3.4.3 development
jshint ^2.9.4 development
jshint-stylish ^2.2.1 development
karma ^1.3.0 development
karma-chrome-launcher ^2.0.0 development
karma-detect-browsers ^2.2.3 development
karma-edge-launcher ^0.2.0 development
karma-electron ^5.1.1 development
karma-firefox-launcher ^1.0.0 development
karma-ie-launcher ^1.0.0 development
karma-jasmine ^1.1.0 development
karma-requirejs ^1.1.0 development
karma-safari-launcher ^1.0.0 development
karma-spec-reporter ^0.0.31 development
mime ^1.3.4 development
mkdirp ^0.5.1 development
request ^2.79.0 development
rimraf ^2.6.1 development
yargs ^7.0.1 development
requirejs ^2.3.2

pt_requirements.txt pypi

matplotlib *
numpy *
opencv-python *
scikit-image *
torch *
torchvision *

tf1_requirements.txt pypi

cdflib *
matplotlib *
protobuf ==3.20.
tensorflow ==1.13.1
tensorflow-gpu ==1.13.1

tf2_requirements.txt pypi

Pillow *
PyQt5 *
joblib *
keras ==2.6.0
mathutils *
matplotlib *
mayavi *
numba *
open3d *
pymeshlab *
sklearn *
tensorflow ==2.6.0
tensorflow-addons *

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science