Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Model
This addresses robustness problems in 3D shape reconstruction for applications like computer graphics and robotics, though it appears incremental as it builds on existing generalizable models.
The paper tackles generalization issues in implicit shape reconstruction from point clouds by combining a neural network's data prior with a shape-specific kernel ridge regression regularization prior, demonstrating improvements over baselines and state-of-the-art methods on synthetic and real data.
Feedforward generalizable models for implicit shape reconstruction from unoriented point cloud present multiple advantages, including high performance and inference speed. However, they still suffer from generalization issues, ranging from underfitting the input point cloud, to misrepresenting samples outside of the training data distribution, or with toplogies unseen at training. We propose here an efficient mechanism to remedy some of these limitations at test time. We combine the inter-shape data prior of the network with an intra-shape regularization prior of a Nyström Kernel Ridge Regression, that we further adapt by fitting its hyperprameters to the current shape. The resulting shape function defined in a shape specific Reproducing Kernel Hilbert Space benefits from desirable stability and efficiency properties and grants a shape adaptive expressiveness-robustness trade-off. We demonstrate the improvement obtained through our method with respect to baselines and the state-of-the-art using synthetic and real data.