Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Model
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 Nystr\"om 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.
Code (1)
Tasks
3D ReconstructionPoint cloud reconstructionSurface ReconstructionSimilar Papers 제목 키워드 기반
SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearization
We present a novel approach for recovering 3D shape and view dependent appearance from a few colored images, enabling efficient 3D reconstruction and novel view synthesis. Our method learns an implicit neural representat…
3D ReconstructionNovel View SynthesisGeneralizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis
This work targets at using a general deep learning framework to synthesize free-viewpoint images of arbitrary human performers, only requiring a sparse number of camera views as inputs and skirting per-case fine-tuning. …
Novel View SynthesisPHRIT: Parametric Hand Representation with Implicit Template
We propose PHRIT, a novel approach for parametric hand mesh modeling with an implicit template that combines the advantages of both parametric meshes and implicit representations. Our method represents deformable hand sh…
3D ReconstructionSingle-View 3D ReconstructionSPAMs: Structured Implicit Parametric Models
Parametric 3D models have formed a fundamental role in modeling deformable objects, such as human bodies, faces, and hands; however, the construction of such parametric models requires significant manual intervention and…
ObjectPatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations
Implicit surface representations, such as signed-distance functions, combined with deep learning have led to impressive models which can represent detailed shapes of objects with arbitrary topology. Since a continuous fu…
Point Cloud Completion