Affiliation:
1. TU Wien Vienna Austria
2. University of Zürich Zurich Switzerland
3. Adobe Research London UK
Abstract
Abstract3D surface reconstruction from point clouds is a key step in areas such as content creation, archaeology, digital cultural heritage and engineering. Current approaches either try to optimize a non‐data‐driven surface representation to fit the points, or learn a data‐driven prior over the distribution of commonly occurring surfaces and how they correlate with potentially noisy point clouds. Data‐driven methods enable robust handling of noise and typically either focus on a global or a local prior, which trade‐off between robustness to noise on the global end and surface detail preservation on the local end. We propose PPSurf as a method that combines a global prior based on point convolutions and a local prior based on processing local point cloud patches. We show that this approach is robust to noise while recovering surface details more accurately than the current state‐of‐the‐art. Our source code, pre‐trained model and dataset are available at https://github.com/cg‐tuwien/ppsurf.
Funder
Austrian Science Fund
Vienna Science and Technology Fund
Subject
Computer Graphics and Computer-Aided Design
Reference49 articles.
1. [AL20] AtzmonM. LipmanY.:Sal: Sign agnostic learning of shapes from raw data. InIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2020).
2. [AL21] AtzmonM. LipmanY.:SALD: sign agnostic learning with derivatives. InInternational Conference on Learning Representations ICLR(2021).
3. [BM22] BoulchA. MarletR.:POCO: Point convolution for surface reconstruction. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(June2022) pp.6302–6314.
4. [BPM20] BoulchA. PuyG. MarletR.:FKAConv: Feature‐kernel alignment for point cloud convolution. In15th Asian Conference on Computer Vision (ACCV 2020)(2020).
5. [BTBW77] BarrowH. G. TenenbaumJ. M. BollesR. C. WolfH. C.:Parametric correspondence and chamfer matching: Two new techniques for image matching. InIJCAI'77: Proceedings of the 5th International Joint Conference on Artificial Intelligence ‐ Volume 2(San Francisco CA USA 1977) Morgan Kaufmann Publishers Inc. pp.659–663.http://dl.acm.org/citation.cfm?id=1622943.1622971