Python interface for H3DS dataset
This repository contains some utilities for using the H3DS dataset introduced in H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction
The H3DS dataset is available only for academic purposes. To request access, start by filling the contact form with your academic email and a license agreement will be sent back, which must be completed by a full-time academic staff member. Finally, you'll be provided with a
H3DS_ACCESS_TOKEN to use the dataset.
The simplest way to use the H3DS dataset is by installing it as a pip package:
pip install h3ds
In order to use the dataset, simply import the package in your python scripts.
from h3ds.dataset import H3DS h3ds = H3DS(path='local/path/to/h3ds')
If it's the first time using H3DS, download the data (less than 500 Mb).
You can easily list the ids of the available scenes
scenes = h3ds.scenes()
and load the data from a concrete scene as:
mesh, images, masks, cameras = h3ds.load_scene(scene_id='1b2a8613401e42a8')
Release history Release notifications | RSS feed
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.