1/1
3 files

Shapenet Illuminants - dataset from "Zero-Shot Day-Night Domain Adaptation with a Physics Prior"

dataset
posted on 12.08.2021, 13:35 by Attila LengyelAttila Lengyel
Shapenet Illuminants is the synthetic classification dataset used in the ICCV '21 publication "Zero-Shot Day-Night Domain Adaptation with a Physics Prior". The images have been rendered from the ShapeNet dataset using the Mitsuba rendering engine. See the readme for more information on using the dataset.

ArXiv: https://arxiv.org/abs/2108.05137
Code: https://github.com/Attila94/CIConv

If you find this dataset useful, please cite:
@article{lengyel2021zeroshot,
title={Zero-Shot Domain Adaptation with a Physics Prior},
author={Attila Lengyel and Sourav Garg and Michael Milford and Jan C. van Gemert},
year={2021},
eprint={2108.05137},
archivePrefix={arXiv},
primaryClass={cs.CV}
}

Funding

Tabula Inscripta: Prior knowledge for deep learning

Netherlands Organisation for Scientific Research

Find out more...

History

Publisher

4TU.ResearchData

Format

image/png

Organizations

TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, Department of Intelligent Systems; QUT Centre for Robotics

Usage metrics

Exports