Source: Awesome
Best Tutorials¶
Fourier Feature Networks and Neural Volume Rendering - Video
Shows how to learning a signal based on Fourier features. Does time series, 2D spatial and 2D volume.
Basics¶
Most Interesting¶
Best Code¶
Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields - Project
nerf2D - Project | Paper | Paper Explained | Code
Plenoxels: Radiance Fields without Neural Networks - Fridovich-Keil & Yu et al (2022) - Project
They used a sparse voxel grid along with a trilinear interpolation field to fill in the missing data. Superfast convergence
pixelNeRF: Neural Radiance Fields from One or Few Images - Yu et al (2021) - Project
They use convolutions to get some global structure. Apparently it works on very few samples.
RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs - Project
They learn from very few samples. They regularize with a normalizing flow.
NeRF-VAE: A Geometry Aware 3D Scene Generative Model - Paper | Talk
Learned Initializations for Optimizing Coordinate-Based Neural Representation - Project
Talks about meta-learning which can be used for some more advanced problems for faster convergence.
Spatio-Temporals¶
Neural Radiance Flow for 4D View Synthesis and Video Processing - Du et al (2021) - Project
Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes - Li et al (2021) - Project
Generative Models¶
Manifold Diffusion Fields - Elhag et. al., 2023 - ARXIV
The authors decompose the coordinate system using the eigen-functions of the Laplace-Beltrami Operator.
Experiments.
They generate unconditional samples for ERA5 data.
Neural Radiance Flow for 4D View Synthesis and Video Processing - Du et al (2021) - ICCV - Project
Random Fourier Features¶
Random Feature Expansions for Deep Gaussian Processes - Cutajar et al - Thesis
On the Error of Random Fourier Features - Paper |
Fourier Operators¶
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains - Project | Code Demo
Fourier Neural Operator for Parametric Partial Differential Equations - Paper | Code | Project | Paper Explained | Anima AnandKumar
SIREN: Implicit Neural Representations with Periodic Activation Functions - Paper Explained | Project | Jax | PyTorch
- Elhag, A. A., Wang, Y., Susskind, J. M., & Bautista, M. A. (2023). Manifold Diffusion Fields. arXiv. 10.48550/ARXIV.2305.15586