OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Isabella, Chen, Linghao, Fu, Ziyang, Wu, Liwen, Jin, Haian, Li, Zhong, Wong, Chin Ming Ryan, Xu, Yi, Ramamoorthi, Ravi, Xu, Zexiang, Su, Hao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909089647296512
author Liu, Isabella
Chen, Linghao
Fu, Ziyang
Wu, Liwen
Jin, Haian
Li, Zhong
Wong, Chin Ming Ryan
Xu, Yi
Ramamoorthi, Ravi
Xu, Zexiang
Su, Hao
author_facet Liu, Isabella
Chen, Linghao
Fu, Ziyang
Wu, Liwen
Jin, Haian
Li, Zhong
Wong, Chin Ming Ryan
Xu, Yi
Ramamoorthi, Ravi
Xu, Zexiang
Su, Hao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2309_07921
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects
Liu, Isabella
Chen, Linghao
Fu, Ziyang
Wu, Liwen
Jin, Haian
Li, Zhong
Wong, Chin Ming Ryan
Xu, Yi
Ramamoorthi, Ravi
Xu, Zexiang
Su, Hao
Computer Vision and Pattern Recognition
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.
title OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.07921