# Learning a Neural 3D Texture Space from 2D Exemplars

arXiv: https://arxiv.org/abs/1912.04158 · HTML: https://mlsanity.com/paper/1912.04158/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2019.

## Built on by (most cited first, 30 of 53)

- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [GeoNeRF: Generalizing NeRF with Geometry Priors](https://mlsanity.com/paper/2111.13539/) (2021)
- [SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image](https://mlsanity.com/paper/2204.00928/) (2022)
- [Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs](https://mlsanity.com/paper/2111.15135/) (2021)
- [MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis](https://mlsanity.com/paper/2103.14910/) (2021)
- [A Structured Dictionary Perspective on Implicit Neural Representations](https://mlsanity.com/paper/2112.01917/) (2021)
- [NeuTex: Neural Texture Mapping for Volumetric Neural Rendering](https://mlsanity.com/paper/2103.00762/) (2021)
- [NeRF-SR: High-Quality Neural Radiance Fields using Supersampling](https://mlsanity.com/paper/2112.01759/) (2021)
- [Texture Generation on 3D Meshes with Point-UV Diffusion](https://mlsanity.com/paper/2308.10490/) (2023)
- [Seeing Implicit Neural Representations as Fourier Series](https://mlsanity.com/paper/2109.00249/) (2021)
- [Generative Modelling of BRDF Textures from Flash Images](https://mlsanity.com/paper/2102.11861/) (2021)
- [RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis](https://mlsanity.com/paper/2205.07058/) (2022)
- [TexSliders: Diffusion-Based Texture Editing in CLIP Space](https://mlsanity.com/paper/2405.00672/) (2024)
- [NeuSample: Neural Sample Field for Efficient View Synthesis](https://mlsanity.com/paper/2111.15552/) (2021)
- [UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomography](https://mlsanity.com/paper/2202.10847/) (2022)
- [Plan2Scene: Converting Floorplans to 3D Scenes](https://mlsanity.com/paper/2106.05375/) (2021)
- [Neural Shell Texture Splatting: More Details and Fewer Primitives](https://mlsanity.com/paper/2507.20200/) (2025)
- [CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture](https://mlsanity.com/paper/2201.12425/) (2022)
- [Random Weight Factorization Improves the Training of Continuous Neural Representations](https://mlsanity.com/paper/2210.01274/) (2022)
- [SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene](https://mlsanity.com/paper/2211.17260/) (2022)
- [Mesh Neural Cellular Automata](https://mlsanity.com/paper/2311.02820/) (2023)
- [X-NeRF: Explicit Neural Radiance Field for Multi-Scene 360circ  Insufficient RGB-D Views](https://mlsanity.com/paper/2210.05135/) (2022)
- [Frequency-Modulated Point Cloud Rendering with Easy Editing](https://mlsanity.com/paper/2303.07596/) (2023)
- [Texture Generation with Neural Cellular Automata](https://mlsanity.com/paper/2105.07299/) (2021)
- [3inGAN: Learning a 3D Generative Model from Images of a Self-similar Scene](https://mlsanity.com/paper/2211.14902/) (2022)
- [TUVF: Learning Generalizable Texture UV Radiance Fields](https://mlsanity.com/paper/2305.03040/) (2023)
- [NeRFocus: Neural Radiance Field for 3D Synthetic Defocus](https://mlsanity.com/paper/2203.05189/) (2022)
- [Learning Positional Embeddings for Coordinate-MLPs](https://mlsanity.com/paper/2112.11577/) (2021)
- [GANmouflage: 3D Object Nondetection with Texture Fields](https://mlsanity.com/paper/2201.07202/) (2022)

## Abstract (arXiv)

We propose a generative model of 2D and 3D natural textures with diversity, visual fidelity and at high computational efficiency. This is enabled by a family of methods that extend ideas from classic stochastic procedural texturing (Perlin noise) to learned, deep, non-linearities. The key idea is a hard-coded, tunable and differentiable step that feeds multiple transformed random 2D or 3D fields into an MLP that can be sampled over infinite domains. Our model encodes all exemplars from a diverse set of textures without a need to be re-trained for each exemplar. Applications include texture interpolation, and learning 3D textures from 2D exemplars.