5,336
edits
Neural Fields: Difference between revisions
→Architectures
(Created page with "Neural Fields refers to using neural networks or neural methods to ==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 * [https://arxiv.org/abs...") |
|||
| Line 54: | Line 54: | ||
;Factorized Feature Grids | ;Factorized Feature Grids | ||
* TensoRF | * TensoRF | ||
===Generalzation=== | |||
Generalization mainly focuses on learning a prior over the distribution, similar to what existing image generation network do.<br> | |||
This enables tasks such as view synthesis from a single image, shape completion, or inpainting. | |||
;CNN | |||
* pixelNeRF | |||
;Latent Codes | |||
* [https://arxiv.org/abs/2109.05591 MDIF] | |||
;Hyper Networks | |||
* Light Field Networks | |||
==Applications== | ==Applications== | ||