Erler, PhilippFuentes‐Perez, LizethHermosilla, PedroGuerrero, PaulPajarola, RenatoWimmer, MichaelAlliez, PierreWimmer, Michael2024-03-232024-03-2320241467-8659https://doi.org/10.1111/cgf.15000https://diglib.eg.org/handle/10.1111/cgf150003D 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 or a prior, which trade‐off between robustness to noise on the global end and surface detail preservation on the local end. We propose 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 .Attribution 4.0 International Licensemodelingsurface reconstruction10.1111/cgf.1500012 pages