Voxel Based Dataset for Systematic 3D reconstruction by artificial neural networks (ANNs). A synthetic scalable cube dataset for training, testing and validating artificial neural networks (ANNs) for learning 3D reconstruction without any predefined object categories. This data set comprises 830000 different cubes captured from 12 different viewpoints. Aim: Clarify whether and how ANNs might learn the underlying mathematical principle of multiple view geometry without object categories. J. Schning, T. Behrens, P. Faion, P. Kheiri, G. Heidemann & U. Krumnack. Structure from Motion by Artificial Neural Networks. In Scandinavian Conference on Image Analysis (SCIA), pages: 146-158, ISBN: 978-3-319-59126-1, 2017. Springer International Publishing. DOI:

Related datasets