[Back]


Contributions to Proceedings:

P. Erler, P. Guerrero, S. Ohrhallinger, M. Wimmer, N. Mitra:
"Points2Surf Learning Implicit Surfaces from Point Clouds";
in: "Computer Vision - ECCV 2020", 12350; Springer Verlag (ed.); issued by: Springer Cham; Springer-Verlag Berlin Heidelberg, Berlin, 2020, ISBN: 978-3-030-58557-0, 108 - 124.



English abstract:
A key step in any scanning-based asset creation workflow is to convert unordered point clouds to a surface. Classical methods (e.g., Poisson reconstruction) start to degrade in the presence of noisy and partial scans. Hence, deep learning based methods have recently been proposed to produce complete surfaces, even from partial scans. However, such data-driven methods struggle to generalize to new shapes with large geometric and topological variations. We present Points2Surf, a novel patch-based learning framework that produces accurate surfaces directly from raw scans without normals. Learning a prior over a combination of detailed local patches and coarse global information improves generalization performance and reconstruction accuracy. Our extensive comparison on both synthetic and real data demonstrates a clear advantage of our method over state-of-the-art alternatives on previously unseen classes (on average, Points2Surf brings down reconstruction error by 30% over SPR and by 270%+ over deep learning based SotA methods) at the cost of longer computation times and a slight increase in small-scale topological noise in some cases. Our source code, pre-trained model, and dataset are available on: https://github.com/ErlerPhilipp/points2surf


"Official" electronic version of the publication (accessed through its Digital Object Identifier - DOI)
http://dx.doi.org/10.1007/978-3-030-58558-7_7

Electronic version of the publication:
https://publik.tuwien.ac.at/files/publik_291233.pdf


Created from the Publication Database of the Vienna University of Technology.