Scalable Surface Reconstruction with Delaunay-Graph Neural Networks
This addresses the problem of scalable and robust surface reconstruction for real-life Multi-View Stereo acquisitions, representing an incremental improvement over prior methods.
The paper tackles surface reconstruction from large-scale, defect-laden point clouds by introducing a learning-based method that combines a 3D Delaunay tetrahedralization with a graph neural network and energy model, outperforming existing algorithms on two public benchmarks.
We 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 energy based models, our approach outperforms both learning and non learning-based reconstruction algorithms on two publicly available reconstruction benchmarks. Our code and data is available at https://github.com/raphaelsulzer/dgnn.