Philipp Erler, Paul Guerrero, Stefan Ohrhallinger, Michael Wimmer, Niloy Mitra
Points2Surf: Learning Implicit Surfaces from Point Clouds
In Computer Vision -- ECCV 2020, pages 108-124. October 2020.
[points2surf_paper] [
short video]
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
@inproceedings{erler-2020-p2s, title = "Points2Surf: Learning Implicit Surfaces from Point Clouds", author = "Philipp Erler and Paul Guerrero and Stefan Ohrhallinger and Michael Wimmer and Niloy Mitra", year = "2020", 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 ", month = oct, address = "Cham", booktitle = "Computer Vision -- ECCV 2020", doi = "10.1007/978-3-030-58558-7_7", editor = "Vedaldi, Andrea and Bischof, Horst and Brox, Thomas and Frahm, Jan-Michael", event = "ECCV 2020", isbn = "978-3-030-58558-7", location = "Glasgow, UK (online)", publisher = "Springer International Publishing", series = "Lecture Notes in Computer Science", journal = "Computer Vision – ECCV 2020", volume = "12350", pages = "108--124", keywords = "surface reconstruction, implicit surfaces, point clouds, patch-based, local and global, deep learning, generalization", URL = "https://www.cg.tuwien.ac.at/research/publications/2020/erler-2020-p2s/", }
TU Wien
Institute of Visual Computing & Human-Centered Technology
Favoritenstr. 9-11 / E193-02
A-1040 Vienna
Austria - Europe