Intrinsic Neural Fields: Learning Functions on Manifolds

• URL: http://arxiv.org/abs/2203.07967v2
• Date: Thu, 17 Mar 2022 13:07:55 GMT
• Title: Intrinsic Neural Fields: Learning Functions on Manifolds
• Abstract summary: Intrinsic neural fields combine the advantages of neural fields with the spectral properties of the Laplace-Beltrami operator. We show that intrinsic neural fields can reconstruct high-quality textures from images with state-of-the-art quality. We demonstrate the versatility of intrinsic neural fields by tackling various applications.
• Score: 45.269698580847916
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural fields have gained significant attention in the computer vision community due to their excellent performance in novel view synthesis, geometry reconstruction, and generative modeling. Some of their advantages are a sound theoretic foundation and an easy implementation in current deep learning frameworks. While neural fields have been applied to signals on manifolds, e.g., for texture reconstruction, their representation has been limited to extrinsically embedding the shape into Euclidean space. The extrinsic embedding ignores known intrinsic manifold properties and is inflexible wrt. transfer of the learned function. To overcome these limitations, this work introduces intrinsic neural fields, a novel and versatile representation for neural fields on manifolds. Intrinsic neural fields combine the advantages of neural fields with the spectral properties of the Laplace-Beltrami operator. We show theoretically that intrinsic neural fields inherit many desirable properties of the extrinsic neural field framework but exhibit additional intrinsic qualities, like isometry invariance. In experiments, we show intrinsic neural fields can reconstruct high-fidelity textures from images with state-of-the-art quality and are robust to the discretization of the underlying manifold. We demonstrate the versatility of intrinsic neural fields by tackling various applications: texture transfer between deformed shapes & different shapes, texture reconstruction from real-world images with view dependence, and discretization-agnostic learning on meshes and point clouds.

Related papers

• Expressivity of Shallow Neural Networks Over Finite Fields [5.181088692457079]
  We study the expressivity of shallow neural networks (PNNs) with monomial activation functions over finite fields.<n>We quantify the expressivity by the cardinality of the neuromanifold and derive a natural lower and upper bound.<n>We present an architecture that exhibits a striking difference in the neuromanifolds when considered over a characteristic zero versus a finite-characteristic field.
  arXiv  Detail & Related papers  (2026-07-19T06:02:43Z)
• Manifolds and Modules: How Function Develops in a Neural Foundation Model [5.518605965321172]
  We present a foundation model of neural activity, characterizing each 'neuron' based on its temporal response properties to parametric stimuli.<n>We find that the different processing stages of the model each exhibit qualitatively different representational structures.<n>Overall, we present this work as a study of the inner workings of a prominent neural foundation model, gaining insights into the biological relevance of its internals.
  arXiv  Detail & Related papers  (2025-11-26T20:36:47Z)
• Sparse Autoencoder Neural Operators: Model Recovery in Function Spaces [75.45093712182624]
  We introduce a framework that extends sparse autoencoders (SAEs) to lifted spaces and infinite-dimensional function spaces, enabling mechanistic interpretability of large neural operators (NO)<n>We compare the inference and training dynamics of SAEs, lifted-SAE, and SAE neural operators.<n>We highlight how lifting and operator modules introduce beneficial inductive biases, enabling faster recovery, improved recovery of smooth concepts, and robust inference across varying resolutions, a property unique to neural operators.
  arXiv  Detail & Related papers  (2025-09-03T21:57:03Z)
• Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning [78.88684753303794]
  Deep learning has predominantly advanced through applications in computer vision and natural language processing.<n>Neural operators are a principled way to generalize neural networks to mappings between function spaces.<n>This paper identifies and distills the key principles for constructing practical implementations of mappings between infinite-dimensional function spaces.
  arXiv  Detail & Related papers  (2025-06-12T17:59:31Z)
• Artificial Neural Networks on Graded Vector Spaces [0.0]
  This paper presents a transformative framework for artificial neural networks over graded vector spaces.<n>We extend classical neural networks with graded neurons, layers, and activation functions that preserve structural integrity.<n>Case studies validate the framework's effectiveness, outperforming standard neural networks in tasks such as predicting invariants in weighted projective spaces.
  arXiv  Detail & Related papers  (2024-07-26T18:17:58Z)
• The Dynamic Net Architecture: Learning Robust and Holistic Visual Representations Through Self-Organizing Networks [3.9848584845601014]
  We present a novel intelligent-system architecture called "Dynamic Net Architecture" (DNA) DNA relies on recurrence-stabilized networks and discuss it in application to vision.
  arXiv  Detail & Related papers  (2024-07-08T06:22:10Z)
• Unsupervised representation learning with Hebbian synaptic and structural plasticity in brain-like feedforward neural networks [0.0]
  We introduce and evaluate a brain-like neural network model capable of unsupervised representation learning. The model was tested on a diverse set of popular machine learning benchmarks.
  arXiv  Detail & Related papers  (2024-06-07T08:32:30Z)
• NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory [70.10550467873499]
  We propose NeuralClothSim, a new quasistatic cloth simulator using thin shells. Our memory-efficient solver operates on a new continuous coordinate-based surface representation called neural deformation fields.
  arXiv  Detail & Related papers  (2023-08-24T17:59:54Z)
• A Hierarchical Architecture for Neural Materials [13.144139872006287]
  We introduce a neural appearance model that offers a new level of accuracy. An inception-based core network structure captures material appearances at multiple scales. We encode the inputs into frequency space, introduce a gradient-based loss, and employ it adaptive to the progress of the learning phase.
  arXiv  Detail & Related papers  (2023-07-19T17:00:45Z)
• Top-down inference in an early visual cortex inspired hierarchical Variational Autoencoder [0.0]
  We exploit advances in Variational Autoencoders to investigate the early visual cortex with sparse coding hierarchical VAEs trained on natural images. We show that representations similar to the one found in the primary and secondary visual cortices naturally emerge under mild inductive biases. We show that a neuroscience-inspired choice of the recognition model is critical for two signatures of computations with generative models.
  arXiv  Detail & Related papers  (2022-06-01T12:21:58Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Neural Fields in Visual Computing and Beyond [54.950885364735804]
  Recent advances in machine learning have created increasing interest in solving visual computing problems using coordinate-based neural networks. neural fields have seen successful application in the synthesis of 3D shapes and image, animation of human bodies, 3D reconstruction, and pose estimation. This report provides context, mathematical grounding, and an extensive review of literature on neural fields.
  arXiv  Detail & Related papers  (2021-11-22T18:57:51Z)
• Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control [80.79820002330457]
  We propose a new method for high-quality synthesis of humans from arbitrary viewpoints and under arbitrary controllable poses. Our method achieves better quality than the state-of-the-arts on playback as well as novel pose synthesis, and can even generalize well to new poses that starkly differ from the training poses.
  arXiv  Detail & Related papers  (2021-06-03T17:40:48Z)
• Texture Generation with Neural Cellular Automata [64.70093734012121]
  We learn a texture generator from a single template image. We make claims that the behaviour exhibited by the NCA model is a learned, distributed, local algorithm to generate a texture.
  arXiv  Detail & Related papers  (2021-05-15T22:05:46Z)

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.