We present a new multi-sensor dataset for multi-view 3D surface reconstruction. It includes registered RGB and depth data from sensors of different resolutions and modalities: smartphones, Intel RealSense, Microsoft Kinect, industrial cameras, and structured-light scanner. The scenes are selected to emphasize a diverse set of material properties challenging for existing algorithms. We provide around 1.4 million images of 107 different scenes acquired from 100 viewing directions under 14 lighting conditions. We expect our dataset will be useful for evaluation and training of 3D reconstruction algorithms and for related tasks. The dataset is available at skoltech3d.appliedai.tech.
@article{arxiv.2203.06111,
title = {Multi-sensor large-scale dataset for multi-view 3D reconstruction},
author = {Oleg Voynov and Gleb Bobrovskikh and Pavel Karpyshev and Saveliy Galochkin and Andrei-Timotei Ardelean and Arseniy Bozhenko and Ekaterina Karmanova and Pavel Kopanev and Yaroslav Labutin-Rymsho and Ruslan Rakhimov and Aleksandr Safin and Valerii Serpiva and Alexey Artemov and Evgeny Burnaev and Dzmitry Tsetserukou and Denis Zorin},
journal= {arXiv preprint arXiv:2203.06111},
year = {2023}
}