OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects
Abstract
We introduce OpenIllumination, a real-world dataset containing over 108K images of 64 objects with diverse materials, captured under 72 camera views and a large number of different illuminations. For each image in the dataset, we provide accurate camera parameters, illumination ground truth, and foreground segmentation masks. Our dataset enables the quantitative evaluation of most inverse rendering and material decomposition methods for real objects. We examine several state-of-the-art inverse rendering methods on our dataset and compare their performances. The dataset and code can be found on the project page: https://oppo-us-research.github.io/OpenIllumination.
Cite
Text
Liu et al. "OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects." Neural Information Processing Systems, 2023.Markdown
[Liu et al. "OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects." Neural Information Processing Systems, 2023.](https://mlanthology.org/neurips/2023/liu2023neurips-openillumination/)BibTeX
@inproceedings{liu2023neurips-openillumination,
title = {{OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects}},
author = {Liu, Isabella and Chen, Linghao and Fu, Ziyang and Wu, Liwen and Jin, Haian and Li, Zhong and Wong, Chin Ming Ryan and Xu, Yi and Ramamoorthi, Ravi and Xu, Zexiang and Su, Hao},
booktitle = {Neural Information Processing Systems},
year = {2023},
url = {https://mlanthology.org/neurips/2023/liu2023neurips-openillumination/}
}