Learning Smooth Neural Functions via Lipschitz Regularization

• URL: http://arxiv.org/abs/2202.08345v1
• Date: Wed, 16 Feb 2022 21:24:54 GMT
• Title: Learning Smooth Neural Functions via Lipschitz Regularization
• Authors: Hsueh-Ti Derek Liu, Francis Williams, Alec Jacobson, Sanja Fidler, Or Litany
• Abstract summary: We introduce a novel regularization designed to encourage smooth latent spaces in neural fields. Compared with prior Lipschitz regularized networks, ours is computationally fast and can be implemented in four lines of code.
• Score: 92.42667575719048
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural implicit fields have recently emerged as a useful representation for 3D shapes. These fields are commonly represented as neural networks which map latent descriptors and 3D coordinates to implicit function values. The latent descriptor of a neural field acts as a deformation handle for the 3D shape it represents. Thus, smoothness with respect to this descriptor is paramount for performing shape-editing operations. In this work, we introduce a novel regularization designed to encourage smooth latent spaces in neural fields by penalizing the upper bound on the field's Lipschitz constant. Compared with prior Lipschitz regularized networks, ours is computationally fast, can be implemented in four lines of code, and requires minimal hyperparameter tuning for geometric applications. We demonstrate the effectiveness of our approach on shape interpolation and extrapolation as well as partial shape reconstruction from 3D point clouds, showing both qualitative and quantitative improvements over existing state-of-the-art and non-regularized baselines.

Related papers

• Optimizing 3D Geometry Reconstruction from Implicit Neural Representations [2.3940819037450987]
  Implicit neural representations have emerged as a powerful tool in learning 3D geometry. We present a novel approach that both reduces computational expenses and enhances the capture of fine details.
  arXiv  Detail & Related papers  (2024-10-16T16:36:23Z)
• NeuralMeshing: Differentiable Meshing of Implicit Neural Representations [63.18340058854517]
  We propose a novel differentiable meshing algorithm for extracting surface meshes from neural implicit representations. Our method produces meshes with regular tessellation patterns and fewer triangle faces compared to existing methods.
  arXiv  Detail & Related papers  (2022-10-05T16:52:25Z)
• Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes [38.157373733083894]
  This paper introduces a framework designed to accurately predict piecewise linear mappings of arbitrary meshes via a neural network. The framework is based on reducing the neural aspect to a prediction of a matrix for a single point, conditioned on a global shape descriptor. By operating in the intrinsic gradient domain of each individual mesh, it allows the framework to predict highly-accurate mappings.
  arXiv  Detail & Related papers  (2022-05-05T19:51:13Z)
• Deep Implicit Surface Point Prediction Networks [49.286550880464866]
  Deep neural representations of 3D shapes as implicit functions have been shown to produce high fidelity models. This paper presents a novel approach that models such surfaces using a new class of implicit representations called the closest surface-point (CSP) representation.
  arXiv  Detail & Related papers  (2021-06-10T14:31:54Z)
• Shape As Points: A Differentiable Poisson Solver [118.12466580918172]
  In this paper, we introduce a differentiable point-to-mesh layer using a differentiable formulation of Poisson Surface Reconstruction (PSR) The differentiable PSR layer allows us to efficiently and differentiably bridge the explicit 3D point representation with the 3D mesh via the implicit indicator field. Compared to neural implicit representations, our Shape-As-Points (SAP) model is more interpretable, lightweight, and accelerates inference time by one order of magnitude.
  arXiv  Detail & Related papers  (2021-06-07T09:28:38Z)
• SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes [117.76767853430243]
  We introduce SNARF, which combines the advantages of linear blend skinning for polygonal meshes with neural implicit surfaces. We propose a forward skinning model that finds all canonical correspondences of any deformed point using iterative root finding. Compared to state-of-the-art neural implicit representations, our approach generalizes better to unseen poses while preserving accuracy.
  arXiv  Detail & Related papers  (2021-04-08T17:54:59Z)
• On the Effectiveness of Weight-Encoded Neural Implicit 3D Shapes [38.13954772608884]
  A neural implicit outputs a number indicating whether the given query point in space is inside, outside, or on a surface. Prior works have focused on _latent-encoded_ neural implicits, where a latent vector encoding of a specific shape is also fed as input. A _weight-encoded_ neural implicit may forgo the latent vector and focus reconstruction accuracy on the details of a single shape.
  arXiv  Detail & Related papers  (2020-09-17T23:10:19Z)
• Learning Local Neighboring Structure for Robust 3D Shape Representation [143.15904669246697]
  Representation learning for 3D meshes is important in many computer vision and graphics applications. We propose a local structure-aware anisotropic convolutional operation (LSA-Conv) Our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-21T13:40:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.