Search Results for author:
Found 12 papers, 6 papers with code
Approximately Piecewise E(3) Equivariant Point Networks
Integrating a notion of symmetry into point cloud neural networks is a provably effective way to improve their generalization capability.
Neural Kernel Surface Reconstruction
We present a novel method for reconstructing a 3D implicit surface from a large-scale, sparse, and noisy point cloud.
Frame Averaging for Equivariant Shape Space Learning
A natural way to incorporate symmetries in shape space learning is to ask that the mapping to the shape space (encoder) and mapping from the shape space (decoder) are equivariant to the relevant symmetries.
Frame Averaging for Invariant and Equivariant Network Design
For example, Euclidean motion invariant/equivariant graph or point cloud neural networks.
Augmenting Implicit Neural Shape Representations with Explicit Deformation Fields
Implicit neural representation is a recent approach to learn shape collections as zero level-sets of neural networks, where each shape is represented by a latent code.
Isometric Autoencoders
Two sources of bad generalization are: extrinsic, where the learned manifold possesses extraneous parts that are far from the data; and intrinsic, where the encoder and decoder introduce arbitrary distortion in the low dimensional parameterization.
SALD: Sign Agnostic Learning with Derivatives
Learning 3D geometry directly from raw data, such as point clouds, triangle soups, or unoriented meshes is still a challenging task that feeds many downstream computer vision and graphics applications.
Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance
In this work we address the challenging problem of multiview 3D surface reconstruction.
Implicit Geometric Regularization for Learning Shapes
Representing shapes as level sets of neural networks has been recently proved to be useful for different shape analysis and reconstruction tasks.
SAL: Sign Agnostic Learning of Shapes from Raw Data
Recently, neural networks have been used as implicit representations for surface reconstruction, modelling, learning, and generation.
Controlling Neural Level Sets
In turn, the sample network can be used to incorporate the level set samples into a loss function of interest.
Point Convolutional Neural Networks by Extension Operators
This paper presents Point Convolutional Neural Networks (PCNN): a novel framework for applying convolutional neural networks to point clouds.
Ranked #81 on
3D Point Cloud Classification
on ModelNet40
