Updated readme with NeRF metrics, added a nicer gif

Summary: See title.

Reviewed By: nikhilaravi

Differential Revision: D27658290

fbshipit-source-id: 232550f04df4951f7f3d712047b39e510a2f4209
This commit is contained in:
David Novotny 2021-04-14 09:19:10 -07:00 committed by Facebook GitHub Bot
parent c18ee9d40a
commit 4a9e294436
2 changed files with 11 additions and 1 deletions

Binary file not shown.

Before

Width:  |  Height:  |  Size: 3.2 MiB

After

Width:  |  Height:  |  Size: 4.9 MiB

View File

@ -3,7 +3,7 @@ Neural Radiance Fields in PyTorch3D
This project implements the Neural Radiance Fields (NeRF) from [1].
<img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/master/.github/nerf_project_logo.gif" width="600" height="300"/>
<img src="https://raw.githubusercontent.com/facebookresearch/pytorch3d/master/.github/nerf_project_logo.gif" width="600" height="338"/>
Installation
@ -77,6 +77,16 @@ https://dl.fbaipublicfiles.com/pytorch3d_nerf_data
Attribution: `lego` and `fern` are data from the original code release of [1] in https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1, which are hosted under the CC-BY license (https://creativecommons.org/licenses/by/4.0/) The S3 bucket files contains the same images while the camera matrices have been adjusted to follow the PyTorch3D convention.
#### Quantitative results
Below are the comparisons between our implementation and the official [`TensorFlow code`](https://github.com/bmild/nerf). The speed is measured on NVidia Quadro GP100.
```
+----------------+------------------+------------------+-----------------+
| Implementation | Lego: test PSNR | Fern: test PSNR | training speed |
+----------------+------------------+------------------+-----------------+
| TF (official) | 31.0 | 27.5 | 0.24 sec/it |
| PyTorch3D | 32.7 | 27.9 | 0.18 sec/it |
+----------------+------------------+------------------+-----------------+
```
#### References
[1] Ben Mildenhall and Pratul P. Srinivasan and Matthew Tancik and Jonathan T. Barron and Ravi Ramamoorthi and Ren Ng, NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis, ECCV2020