Sulzer, RaphaelLandrieu, LoicMarlet, RenaudVallet, BrunoDigne, Julie and Crane, Keenan2021-07-102021-07-1020211467-8659https://doi.org/10.1111/cgf.14364https://diglib.eg.org:443/handle/10.1111/cgf14364We introduce a novel learning-based, visibility-aware, surface reconstruction method for large-scale, defect-laden point clouds. Our approach can cope with the scale and variety of point cloud defects encountered in real-life Multi-View Stereo (MVS) acquisitions. Our method relies on a 3D Delaunay tetrahedralization whose cells are classified as inside or outside the surface by a graph neural network and an energy model solvable with a graph cut. Our model, making use of both local geometric attributes and line-of-sight visibility information, is able to learn a visibility model from a small amount of synthetic training data and generalizes to real-life acquisitions. Combining the efficiency of deep learning methods and the scalability of energybased models, our approach outperforms both learning and non learning-based reconstruction algorithms on two publicly available reconstruction benchmarks.Computing methodologiesReconstructionNeural networksShape inference10.1111/cgf.14364157-167