Skip to main content

Python interface for H3DS dataset

Project description

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

Accessing H3DS data

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')

To list the available scenes, simply use:

scenes = h3ds.scenes() # returns all the scenes ['1b2a8613401e42a8', ...]
scenes = h3ds.scenes(tags={'h3d-net'}) # returns the scenes used in H3D-Net paper

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 a mesh, 3 images, 3 masks and 3 cameras.


We provide a method for evaluating your reconstructions with a single line of code

mesh_pred, landmarks_pred = my_rec_method(images, masks, cameras)
chamfer, _, _, _ = h3ds.evaluate_scene('1b2a8613401e42a8', mesh_pred, landmarks_pred)

The landmarks_pred is an optional dictionary containing landmarks used for a coarse alignment between the predicted mesh and the ground truth mesh. Please, check this description of the landmarks positions.

For more insights, check the examples provided.

Comparison against H3D-Net

The results reported in the H3D-Net paper (Table 2) slightly differ from the ones obtained using the evaluation code provided in this repository. This is due to minor implementation changes in the alignment process and in the cutting of the regions. In the following table we provide the results obtained using the evaluation code from this repository. We encourage everyone to use the evaluate_scene method provided in this repository to report comparable results accross different works.

Method \ Views 3 4 8 16 32
IDR 2.79 / 14.58 1.88 / 8.99 1.83 / 8.34 1.31 / 6.37 1.25 / 5.71
H3D-Net 1.33 / 10.52 1.35 / 7.71 1.18 / 6.45 1.05 / 5.36 1.03 / 5.25

The numbers from the table can be obtained by running the evaluation script from the examples folder, which uses the 3D reconstructions from the paper to compute the metrics.

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},

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

h3ds-0.3.3.tar.gz (17.0 kB view hashes)

Uploaded source

Built Distribution

h3ds-0.3.3-py3-none-any.whl (16.6 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page