The H3DS dataset contains high-resolution 3D full-head texture scans and 360º images collected using a structured light scanner. The dataset consists of 23 3D full-head scans, including images, masks, and camera positions. The 3D geometry was collected using a structured light scanner to obtain accurate ground truth geometry.

Citation

@inproceedings{ramon2021h3d,
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},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
pages={5620--5629},
year={2021}
}