Neural Fields

Neural Fields refers to using neural networks or neural methods to represent scenes or other signals in computer vision and graphics.

Techniques

Forward Maps

Forward maps are the differentiable functions which convert the representation to an observed signal.

Shapes

Occupancy Grids or Voxel Grids

Signed Distance Functions

Primary-ray (PRIF)

3D Scenes

Radiance Fields (NeRF)

Light Fields

Identity

Images

Architectures

Neural Networks

MLP

CNN + MLP

• pixelNeRF

Progressive Architectures

• Streamable Neural Fields

Hybrid Representations

Voxel Grids

These typically combine a octree or voxel grid with an MLP.
Some of these are basically feature grids.

• Neural Sparse Voxel Fields
• KiloNeRF

Point Clouds

Mesh

Feature Grids

Plenoxels

Plenoctrees

Hash (Instant-NGP)

Vector Quantization

https://nv-tlabs.github.io/vqad/

Factorized Feature Grids

• TensoRF

Generalization

Generalization mainly focuses on learning a prior over the distribution, similar to what existing image generation network do.
This enables more advanced vision tasks such as view synthesis from a single image, shape completion, inpainting, object generation, segmentation.

CNN

• pixelNeRF

Latent Codes

• MDIF

Hyper Networks

• Light Field Networks

Applications

3D Generation

• EG3D - Adapting Stylegan2, NeRF, and a super-resolution network for generating 3D scenes
• Dream Fields - CLIP-guided NeRF generation
• Dreamfusion - Adapting text-to-image diffusion models to generate NeRFs

Resources

• CVPR 2022 Tutorial on Neural Fields in Computer Vision
• State of the Art on Neural Rendering (Tewari et al., 2020)
• Advances in Neural Rendering (Tewari et al., 2021)