Neural Fields: Difference between revisions

From David's Wiki
No edit summary
Line 53: Line 53:
;Factorized Feature Grids
;Factorized Feature Grids
* TensoRF
* TensoRF
===Dynamic Content===
====Deformation====
The idea here is to have an MLP which models the deformation of a canonical frame to the target frame.
* [https://www.albertpumarola.com/research/D-NeRF/index.html D-NeRF (CVPR 2020)]
* [https://hypernerf.github.io/ HyperNeRF (SIGGRAPH Asia 2021)]
====Latent code====
Use a latent code for each time step.
* [https://neural-3d-video.github.io/ Neural 3D Video Synthesis (CVPR 2022)]
* [https://arxiv.org/abs/2210.15947 NeRFPlayer]
** Use a time-dependent sliding window along the feature channels in a feature grid.
====Time-axis====
* [https://arxiv.org/abs/2301.11280 Text-To-4D Dynamic Scene Generation (2023)]
** Extends the tri-plane feature grid to a six-plane feature grid ({x, y, z, t} choose 2).
====Segmentation====
Segment static background and objects from dynamic background and objects
* [https://arxiv.org/abs/2303.03361 NeRFlets (2023)]
* [https://arxiv.org/abs/2303.14536 SUDS: Scalable Urban Dynamic Scenes (2023)]


===Generalization===
===Generalization===

Revision as of 15:13, 30 March 2023

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
Progressive Architectures

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

Dynamic Content

Deformation

The idea here is to have an MLP which models the deformation of a canonical frame to the target frame.

Latent code

Use a latent code for each time step.

Time-axis

Segmentation

Segment static background and objects from dynamic background and objects

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
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