We present a detail-driven deep neural network for point set upsampling. A high-resolution point set is essential for point-based rendering and surface reconstruction. Inspired by the recent success of neural image super-resolution techniques, we progressively train a cascade of patch-based upsampling networks on different levels of detail end-to-end. We propose a series of architectural design contributions that lead to a substantial performance boost. The effect of each technical contribution is demonstrated in an ablation study. Qualitative and quantitative experiments show that our method significantly outperforms the state-of-the-art learning-based and optimazation-based approaches, both in terms of handling low-resolution inputs and revealing high-fidelity details.
PU-Net: L. Yu, X. Li, C.-W. Fu, D. Cohen-Or, and P.-A. Heng, “Pu-net: Point cloud upsampling network”, CVPR 2018
EC-Net: L. Yu, X. Li, C.-W. Fu, D. Cohen-Or, and P.-A. Heng, “Ec-net: an edge-aware point set consolidation network”, ECCV 2018
EAR: H. Huang, S. Wu, M. Gong, D. Cohen-Or, U. Ascher, and H. Zhang, “Edge-aware point set resampling”, ACM ToG 2013
WLOP: H. Huang, D. Li, H. Zhang, U. Ascher, and D. Cohen-Or, “Consolidation of unorganized point clouds for surface reconstruction”, SIGGRAPH Asia 2009