ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds
This work addresses the challenge of robust and repeatable surface parametrization for 3D point clouds, particularly in man-made shapes, offering an incremental improvement over existing learning-based and geometric approaches.
The paper tackles the problem of decomposing 3D point clouds into parametric surface patches, proposing ParSeNet, an end-to-end trainable deep network that handles a richer class of primitives and achieves higher fidelity surface representation compared to prior methods.
We propose a novel, end-to-end trainable, deep network called ParSeNet that decomposes a 3D point cloud into parametric surface patches, including B-spline patches as well as basic geometric primitives. ParSeNet is trained on a large-scale dataset of man-made 3D shapes and captures high-level semantic priors for shape decomposition. It handles a much richer class of primitives than prior work, and allows us to represent surfaces with higher fidelity. It also produces repeatable and robust parametrizations of a surface compared to purely geometric approaches. We present extensive experiments to validate our approach against analytical and learning-based alternatives. Our source code is publicly available at: https://hippogriff.github.io/parsenet.