DNerf-Pytorch
Implementation of paper D-Nerf: Neural Randiance Fields for Dynamic Scenes
| Nerf (v18) | T-Nerf (v2) |
|---|---|
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
Novel Views
| Camera | Time | Camera + Time |
|---|---|---|
 |
 |
 |
Hyperparameters:
| Parameters | Values |
|---|---|
| Iteration | 200K |
| Scheduler | Exponential Decay |
| Scheduler Step | 160K approx. |
| Rays Sample | 1024 |
| Crop | 0.5 |
| Pre Crop Iter | 50 |
| Factor | 2 |
| Near Plane | 2.0 |
| Far Plane | 6.0 |
| Height | 800 / factor |
| Width | 800 / factor |
| Downscale | 2 |
| lr | 5e-4 |
| lrsch_gamma | 0.1 |
| Pos Enc Dim | 10 |
| Dir Enc Dim | 4 |
| Num Samples | 64 |
| Num Samples Fine | 128 |
| Net Dim | 256 |
| Net Depth | 8 |
| Inp Feat | 2*(num_channels*pos_enc_dim) + num_channels |
| Dir Feat | 2*(num_channels*dir_enc_dim) + num_channels |
| Time Feat | 2*(1*dir_enc_dim) + 1 |
References:
[1] Computer Graphics and Deep Learning with NeRF using TensorFlow and Keras []
[2] 3D volumetric rendering with NeRF []
[3] Nerf Official Colab Notebook []
[4] NeRF PyTorch [] ( Special Thanks :) )
[5] PyTorch Image Quality (PIQ) []