Is Gaussian Splatting Becoming Neural Again? A Taxonomy and Controlled Study of Learned Parameterization

• URL: http://arxiv.org/abs/2609.12395v1
• Date: Fri, 11 Sep 2026 03:37:31 GMT
• Title: Is Gaussian Splatting Becoming Neural Again? A Taxonomy and Controlled Study of Learned Parameterization
• Abstract summary: Three-dimensional Gaussian Splatting (3DGS) combines explicit primitives with efficientization.<n>Recent systems increasingly use neural networks to generate or share Gaussian parameters.<n>We characterize this trend along five axes: attribute decoding, spatial sharing, view-conditioned decoding, topology generation, and amortized inference.
• Score: 6.732693952041468
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Three-dimensional Gaussian Splatting (3DGS) combines explicit primitives with efficient rasterization, yet recent systems increasingly use neural networks to generate or share Gaussian parameters. We characterize this trend along five axes: attribute decoding, spatial sharing, view-conditioned decoding, topology generation, and amortized inference. An analysis of 19 representative methods shows that these choices address different limitations and cannot be reduced to a binary neural label. We also isolate three forms of neural parameterization in a controlled mip-NeRF 360 study. Sharing appearance and opacity improves reconstruction quality, while decoding geometric structure offers no further gain. The evidence favors selective neuralization: shared functions help when they capture reusable correlations without sacrificing the local geometric freedom of explicit splats.

Related papers

• Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction [21.360321969322047]
  We introduce Neural Harmonic Textures, a neural representation approach that anchors latent feature vectors on a virtual scaffold surrounding each primitive.<n>Inspired by Fourier analysis, we apply periodic activations to the interpolated features, turning alpha blending into a weighted sum of harmonic components.<n>Our method integrates seamlessly into existing primitive-based pipelines such as 3DGUT, Triangle Splatting, and 2DGS.
  arXiv  Detail & Related papers  (2026-04-01T17:48:22Z)
• Learning Unified Representation of 3D Gaussian Splatting [15.792493458115016]
  A well-designed vectorized representation is crucial for the learning systems native to 3D Gaussian Splatting.<n>We propose an embedding representation of 3DGS based on continuous submanifold fields that encapsulate the intrinsic information of Gaussian primitives.
  arXiv  Detail & Related papers  (2025-09-26T20:44:59Z)
• HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis [11.71939856454585]
  We present Hybrid Radiance Fields (HyRF), a novel scene representation that combines the strengths of explicit Gaussians and neural fields.<n>HyRF achieves state-of-the-art rendering quality while reducing model size by over 20 times compared to 3DGS.
  arXiv  Detail & Related papers  (2025-09-21T13:59:26Z)
• Point Cloud Denoising With Fine-Granularity Dynamic Graph Convolutional Networks [58.050130177241186]
  Noise perturbations often corrupt 3-D point clouds, hindering downstream tasks such as surface reconstruction, rendering, and further processing. This paper introduces finegranularity dynamic graph convolutional networks called GDGCN, a novel approach to denoising in 3-D point clouds.
  arXiv  Detail & Related papers  (2024-11-21T14:19:32Z)
• Graph Neural Networks for Learning Equivariant Representations of Neural Networks [55.04145324152541]
  We propose to represent neural networks as computational graphs of parameters. Our approach enables a single model to encode neural computational graphs with diverse architectures. We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations.
  arXiv  Detail & Related papers  (2024-03-18T18:01:01Z)
• Unsupervised Learning of Invariance Transformations [105.54048699217668]
  We develop an algorithmic framework for finding approximate graph automorphisms. We discuss how this framework can be used to find approximate automorphisms in weighted graphs in general.
  arXiv  Detail & Related papers  (2023-07-24T17:03:28Z)
• Permutation Equivariant Neural Functionals [92.0667671999604]
  This work studies the design of neural networks that can process the weights or gradients of other neural networks. We focus on the permutation symmetries that arise in the weights of deep feedforward networks because hidden layer neurons have no inherent order. In our experiments, we find that permutation equivariant neural functionals are effective on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-02-27T18:52:38Z)
• Orders-of-coupling representation with a single neural network with optimal neuron activation functions and without nonlinear parameter optimization [0.0]
  We show that neural network models of orders-of-coupling representations can be easily built by using a recently proposed neural network with optimal neuron activation functions. Examples are given of representations of molecular potential energy surfaces.
  arXiv  Detail & Related papers  (2023-02-11T06:27:26Z)
• Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensembles [3.625425081454343]
  Systems neuroscience relies on two complementary views of neural data, characterized by single neuron tuning curves and analysis of population activity. These two perspectives combine elegantly in neural latent variable models that constrain the relationship between latent variables and neural activity. We propose feature sharing across neural tuning curves, which significantly improves performance and leads to better-behaved optimization.
  arXiv  Detail & Related papers  (2022-10-06T18:37:49Z)
• Spiking neural network for nonlinear regression [68.8204255655161]
  Spiking neural networks carry the potential for a massive reduction in memory and energy consumption. They introduce temporal and neuronal sparsity, which can be exploited by next-generation neuromorphic hardware. A framework for regression using spiking neural networks is proposed.
  arXiv  Detail & Related papers  (2022-10-06T13:04:45Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)

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.