5,350
edits
Line 25: | Line 25: | ||
;MLP | ;MLP | ||
* SIREN | |||
** Proposes using sine activation to remove the spectrial bias instead of positional encoding. | |||
* [https://arxiv.org/pdf/2104.09125.pdf SAPE] | |||
** Progressively exposes additional frequencies during training based on time and space. | |||
;CNN + MLP | ;CNN + MLP | ||
Line 39: | Line 43: | ||
* Neural Sparse Voxel Fields | * Neural Sparse Voxel Fields | ||
* KiloNeRF | * KiloNeRF | ||
** Uses thousands of small voxels, each modelled by a single NeRF. Optimized using a teacher network. | |||
;Point Clouds | ;Point Clouds | ||
Line 45: | Line 50: | ||
====Feature Grids==== | ====Feature Grids==== | ||
* Plenoctrees | |||
** Convert a NeRF into a octree of spherical harmonics for fast rendering. | |||
* Plenoxels | |||
** Directly use a voxel grid of spherical harmonics to fast optimization and rendering. | |||
https://nv-tlabs.github.io/vqad/ | * Hash (Instant-NGP) | ||
** Use a hash function map voxels to features in a codebook. Disconnects grid resolution from codebook size. | |||
* [https://nv-tlabs.github.io/vqad/ Variable Bitrate Neural Fields] | |||
** Use vector quantization to compress feature grids. However, need to store an grid of indices. | |||
;Factorized Feature Grids | ;Factorized Feature Grids |