View source for Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering

Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering

Authors:Vincent Sitzmann, Semon Rezchikov, William T. Freeman, Joshua B. Tenenbaum, Fredo Durand<br>
Affiliations: MIT
Links [https://arxiv.org/abs/2106.02634 https://arxiv.org/abs/2106.02634]

==Method==
===Background===
See NeRF and SIREN.

===Light Field Networks===
The idea here is to use light field rendering instead of volume rendering or SDF ray marching.<br>
In this case, the input to the network is the entire ray rather than the a single 3D point.<br>
Thus, it is not necessary to sample across the entire ray and composite the samples.

===Plucker coordinates===
{{ main | Wikipedia: Plücker_coordinates}}
They use Plucker coordinates to encode rays instead of directly inputting the (point, direction) representation or using a two-plane parameterization.<br>
The benefit is that Plucker coordinates are invariance to the selected point and can represent the entire 360 set of rays.<br>
<math>\mathbf{r} = (\mathbf{d},\mathbf{m}) \in \mathbb{R}^6</math> where <math>\mathbf{m}=\mathbf{p} \times \mathbf{d}</math>

===Geometry===
(NOT FILLED IN)<br>
There is some interesting discussion in the paper about the point-line isomorphism, epipolar plane image, and how to extract depth.

===Metalearning===
They use a hypernetwork to convert latent codes to scenes represented by the networks.

==Evaluation==
[[Category: Papers]]