static.rst 4.18 KB
Newer Older
1
2
3
4
5
6
7
8
9
Static NeRFs
===================================

Performance Overview
--------------------

+----------------------+----------------+----------------------------------+-----------------------+--------------------------+
| Methods              | Dataset        | Training Time :math:`\downarrow` | PSNR :math:`\uparrow` | LPIPS :math:`\downarrow` |
+======================+================+==================================+=======================+==========================+
10
| TensoRF `[1]`_       | Tanks&Temple   | 19min                            | 28.11                 | 0.167                    |
11
+----------------------+----------------+----------------------------------+-----------------------+--------------------------+
12
| *+nerfacc (occgrid)* |                | 14min                            | 28.06                 | 0.174                    |
13
+----------------------+----------------+----------------------------------+-----------------------+--------------------------+
14
| TensoRF `[1]`_       | NeRF-Synthetic | 10.3min                          | 32.73                 | 0.049                    |
15
+----------------------+----------------+----------------------------------+-----------------------+--------------------------+
16
| *+nerfacc (occgrid)* |                | 7.1min                           | 32.52                 | 0.054                    |
17
+----------------------+----------------+----------------------------------+-----------------------+--------------------------+
18
| NeRF `[2]`_          | NeRF-Synthetic | days                             | 31.00                 | 0.047                    |
19
+----------------------+----------------+----------------------------------+-----------------------+--------------------------+
20
| *+nerfacc (occgrid)* |                | 1hr                              | 31.55                 | 0.072                    |
21
22
23
+----------------------+----------------+----------------------------------+-----------------------+--------------------------+
| Instant-NGP `[3]`_   | NeRF-Synthetic | 4.4min                           | 32.35                 |                          |
+----------------------+----------------+----------------------------------+-----------------------+--------------------------+
24
| *+nerfacc (occgrid)* |                | 4.5min                           | 33.11                 | 0.053                    |
25
+----------------------+----------------+----------------------------------+-----------------------+--------------------------+
26
| *+nerfacc (propnet)* |                | 4.0min                           | 31.76                 | 0.062                    |
27
28
29
+----------------------+----------------+----------------------------------+-----------------------+--------------------------+
| Instant-NGP `[3]`_   | Mip-NeRF 360   | 5.3min                           | 25.93                 |                          |
+----------------------+----------------+----------------------------------+-----------------------+--------------------------+
30
| *+nerfacc (occgrid)* |                | 5.0min                           | 26.41                 | 0.353                    |
31
+----------------------+----------------+----------------------------------+-----------------------+--------------------------+
32
| *+nerfacc (propnet)* |                | 4.9min                           | 27.58                 | 0.292                    |
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
+----------------------+----------------+----------------------------------+-----------------------+--------------------------+

Implementation Details
----------------------

.. toctree::
   :glob:
   :maxdepth: 1

   static/*

|

3rd-Party Use Cases
-------------------

- `nerfstudio <https://docs.nerf.studio/>`_: A collaboration friendly studio for NeRFs.
- `modelscope <https://github.com/modelscope/modelscope/blob/master/modelscope/models/cv/nerf_recon_acc/network/nerf.py>`_: A collection of deep-learning algorithms.
- `sdfstudio <https://autonomousvision.github.io/sdfstudio/>`_: A Unified Framework for Surface Reconstruction.
- `instant-nsr-pl <https://github.com/bennyguo/instant-nsr-pl>`_: Train NeuS in 10min.

.. _`[1]`: https://arxiv.org/abs/2203.09517
.. _`[2]`: https://arxiv.org/abs/2003.08934
.. _`[3]`: https://arxiv.org/abs/2201.05989