1. PASMVS: a perfectly accurate, synthetic, path-traced dataset featuring specular material properties for multi-view stereopsis training and reconstruction applications;Broekman;Data Br.,2020
2. A. Broekman, P.J. Gräbe, RailEnV-PASMVS: a dataset for multi-view stereopsis training and reconstruction applications (2021), Zenodo, V2. 10.5281/zenodo.5233840
3. Recurrent MVSNet for high-resolution multi-view stereo depth inference;Yao,2019
4. MVSNet++: learning depth-based attention pyramid features for multi-view stereo;Chen;IEEE Tran. Image Process.,2020
5. Y. Yao, Z. Luo, S. Li, J. Zhang, Y. Ren, L. Zhou, T. Fang, L. Quan, BlendedMVS: a large-scale dataset for generalised multi-view stereo networks. https://fr.arxiv.org/abs/1911.10127v1