5,337
edits
Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering: Difference between revisions
Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering (view source)
Revision as of 15:23, 30 August 2021
, 30 August 2021→Light Field Networks
| Line 11: | Line 11: | ||
===Light Field Networks=== | ===Light Field Networks=== | ||
The idea here is to use light field rendering instead of volume rendering or SDF ray marching.<br> | 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 | 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. | Thus, it is not necessary to sample across the entire ray and composite the samples. | ||