H3DS Dataset

This repository contains the code for using the H3DS dataset introduced in H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction


The H3DS dataset is only available for non-commercial research purposes. To request access, please fill in the contact form with your academic email. Your application will be reviewed and, after acceptance, you will recieve a H3DS_ACCESS_TOKEN together with the license and terms of use.


The simplest way to use the H3DS dataset is by installing it as a pip package:

pip install h3ds

Using H3DS

You can start using H3DS in your project with a few lines of code

from h3ds.dataset import H3DS

h3ds = H3DS(path='local/path/to/h3ds')
mesh, images, masks, cameras = h3ds.load_scene(scene_id='1b2a8613401e42a8')

The returned types when loading a scene are Trimesh, list(PIL.Image) list(PIL.Image) and list(tuple(np.ndarray)).

To list the available scenes, simply use:

scenes = h3ds.scenes() # ['1b2a8613401e42a8', ...]

In order to reproduce the results from H3D-Net, we provide default views configurations for each scene:

views_configs = h3ds.default_views_configs(scene_id='1b2a8613401e42a8') # '3', '4', '8', '16' and '32'
mesh, images, masks, cameras = h3ds.load_scene(scene_id='1b2a8613401e42a8', views_config_id='3')

This will load a scene with 3 images, 3 masks and 3 cameras.

Please, see the provided examples for more insights.

Terms of use

By using the H3DS Dataset you agree with the following terms:

  1. The data must be used for non-commercial research and/or education purposes only.
  2. You agree not to copy, sell, trade, or exploit the data for any commercial purposes.
  3. If you will be publishing any work using this dataset, please cite the original paper.


  title={H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction},
  author={Ramon, Eduard and Triginer, Gil and Escur, Janna and Pumarola, Albert and Garcia, Jaime and Giro-i-Nieto, Xavier and Moreno-Noguer, Francesc},
  journal={arXiv preprint arXiv:2107.12512},