# Learning View-Dependent Splatting Kernels

arXiv: https://arxiv.org/abs/2605.25426 · HTML: https://mlsanity.com/paper/2605.25426/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 22 of 22)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [3D Gaussian Splatting as Markov Chain Monte Carlo](https://mlsanity.com/paper/2404.09591/) (2024)
- [3D Gaussian as a New Era: A Survey](https://mlsanity.com/paper/2402.07181/) (2024)
- [GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering](https://mlsanity.com/paper/2402.10128/) (2024)
- [Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting](https://mlsanity.com/paper/2402.15870/) (2024)
- [DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting](https://mlsanity.com/paper/2504.00773/) (2025)
- [3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes](https://mlsanity.com/paper/2411.14974/) (2024)
- [Triangle Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2505.19175/) (2025)
- [GS^3: Efficient Relighting with Triple Gaussian Splatting](https://mlsanity.com/paper/2410.11419/) (2024)
- [Textured Gaussians for Enhanced 3D Scene Appearance Modeling](https://mlsanity.com/paper/2411.18625/) (2024)
- [RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination](https://mlsanity.com/paper/2505.21925/) (2025)
- [Beyond Gaussians: Fast and High-Fidelity 3D Splatting with Linear Kernels](https://mlsanity.com/paper/2411.12440/) (2024)
- [MeshSplatting: Differentiable Rendering with Opaque Meshes](https://mlsanity.com/paper/2512.06818/) (2025)
- [Does 3D Gaussian Splatting Need Accurate Volumetric Rendering?](https://mlsanity.com/paper/2502.19318/) (2025)
- [Perceptual Quality Assessment of NeRF and Neural View Synthesis Methods for Front-Facing Views](https://mlsanity.com/paper/2303.15206/) (2023)
- [Neural Shell Texture Splatting: More Details and Fewer Primitives](https://mlsanity.com/paper/2507.20200/) (2025)
- [Splat the Net: Radiance Fields with Splattable Neural Primitives](https://mlsanity.com/paper/2510.08491/) (2025)
- [SpecGaussian with Latent Features: A High-quality Modeling of the View-dependent Appearance for 3D Gaussian Splatting](https://mlsanity.com/paper/2409.05868/) (2024)
- [3D Gabor Splatting: Reconstruction of High-frequency Surface Texture using Gabor Noise](https://mlsanity.com/paper/2504.11003/) (2025)
- [Content-Aware Texturing for Gaussian Splatting](https://mlsanity.com/paper/2512.02621/) (2025)

## Abstract (arXiv)

We present a differentiable framework to automatically learn view-dependent 2D kernels in a splatting-based pipeline to improve reconstruction quality and representation efficiency for novel 3D view synthesis. Our volumetric primitive is defined as a bounding ellipsoid and a 3D-kernel latent vector. We first learn a projection network to output a 2D-kernel latent, taking the attributes of the ellipsoid and the 3D-kernel latent as input. Next, the result is sent to a decoder to produce a radially symmetric 2D kernel in terms of Mahalanobis distance, bounded by the projected ellipsoid. The neural networks along with per-primitive attributes are jointly optimized. The effectiveness of our approach is demonstrated on standard benchmarks, comparing favorably against state-of-the-art techniques on both analytical and learned kernels. Finally, we extend the idea to learn general 2D kernels for 2D splatting as well as image representation.