InteriorVerse: Large-scale Photorealistic Indoor Scene Dataset

Jingsen Zhu1, Fujun Luan2, Yuchi Huo1,3, Zihao Lin1, Zhihua Zhong1, Dianbing Xi1, Jiaxiang Zheng4, Rui Tang4 Rui Wang1, Hujun Bao1,
1State Key Lab of CAD&CG, Zhejiang University, 2Adobe Research, 3Zhejiang Lab, 4KooLab, Manycore

SIGGRAPH Asia 2022 (Conference Proceedings)

InteriorVerse is a large-scale photorealistic indoor scene dataset proposed by paper Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing in SIGGRAPH Asia'22 conference proceedings. It contains synthetic rendering results of over 4000 indoor scenes with ground truth material, geometry and spatially-varying lightings.

Dataset Overview

InteriorVerse provides a large-scale dataset with ground truth synthetic material and geometry annotations, containing over 50,000 images in over 4,000 well-designed indoor scenes.
InteriorVerse also provides ground truth HDR lighting data for 1,000 indoor scenes. Each scene contains hundreds of spatially-varying environment maps with known camera positions.

Download

You can download our preview dataset containing 10 example scenes [HERE].
For access to our full dataset, please agree to the terms of use [HERE], and send an e-mail titled [InteriorVerse Dataset Request]: < your organization > to interiorverse@qunhemail.com. After receiving your agreement form, the links to our full dataset will be sent. Many thanks for your patience. If you use any part of our dataset/code, please cite our paper. For more details of data format and usage, please refer to our [README].
Kujiale.com will reserve the right of the assets including furniture models, layouts and scenes, used in this dataset.

Acknowledgements

We would like to thank Kujiale.com for providing their database of production furniture models and layouts. We also thank the Kujiale artists and other professionals for their great efforts into editing and labelling millions of models and scenes. We also highly appreciate comments and technical support from Kujiale Rendering Group, as well as helpful discussions and comments from Prof. Rui Wang and other members of Rendering Group of State Key Lab of CAD&CG, Zhejiang University.

BibTeX

@inproceedings{zhu2022learning,
    author = {Zhu, Jingsen and Luan, Fujun and Huo, Yuchi and Lin, Zihao and Zhong, Zhihua and Xi, Dianbing and Wang, Rui and Bao, Hujun and Zheng, Jiaxiang and Tang, Rui},
    title = {Learning-Based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing},
    year = {2022},
    publisher = {ACM},
    url = {https://doi.org/10.1145/3550469.3555407},
    booktitle = {SIGGRAPH Asia 2022 Conference Papers},
    articleno = {6},
    numpages = {8}
}