Merge pull request bmild#5 from bmild/colab_example

Add colab example
akuganesan · Mar 22, 2020 · fa829f7 · fa829f7
2 parents 98d3ebf + 0f97fc5
commit fa829f7
Show file tree

Hide file tree

Showing 2 changed files with 1,983 additions and 652 deletions.
diff --git a/README.md b/README.md
@@ -1,17 +1,17 @@
 # NeRF: Neural Radiance Fields
-### [Project](http://tancik.com/nerf) | [Video](https://youtu.be/JuH79E8rdKc) | [Paper](https://arxiv.org/abs/2003.08934) 
-
+### [Project](http://tancik.com/nerf) | [Video](https://youtu.be/JuH79E8rdKc) | [Paper](https://arxiv.org/abs/2003.08934)
+[![Open Tiny-NeRF in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/bmild/nerf/blob/master/tiny_nerf.ipynb)<br>
 Tensorflow implementation of optimizing a neural representation for a single scene and rendering new views.<br><br>
 [NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis](http://tancik.com/nerf)  
- [Ben Mildenhall](https://people.eecs.berkeley.edu/~bmild/)\*<sup>1</sup>, 
- [Pratul P. Srinivasan](https://people.eecs.berkeley.edu/~pratul/)\*<sup>1</sup>, 
- [Matthew Tancik](http://tancik.com/)\*<sup>1</sup>, 
- [Jonathan T. Barron](http://jonbarron.info/)<sup>2</sup>, 
- [Ravi Ramamoorthi](http://cseweb.ucsd.edu/~ravir/)<sup>3</sup>, 
+ [Ben Mildenhall](https://people.eecs.berkeley.edu/~bmild/)\*<sup>1</sup>,
+ [Pratul P. Srinivasan](https://people.eecs.berkeley.edu/~pratul/)\*<sup>1</sup>,
+ [Matthew Tancik](http://tancik.com/)\*<sup>1</sup>,
+ [Jonathan T. Barron](http://jonbarron.info/)<sup>2</sup>,
+ [Ravi Ramamoorthi](http://cseweb.ucsd.edu/~ravir/)<sup>3</sup>,
  [Ren Ng](https://www2.eecs.berkeley.edu/Faculty/Homepages/yirenng.html)<sup>1</sup> <br>
  <sup>1</sup>UC Berkeley, <sup>2</sup>Google Research, <sup>3</sup>UC San Diego  
   \*denotes equal contribution  
-  
+
 
 <img src='imgs/pipeline.jpg'/>
 
@@ -20,7 +20,7 @@ Tensorflow implementation of optimizing a neural representation for a single sce
 
 Python 3 dependencies:
 
-* Tensorflow 1.15 
+* Tensorflow 1.15
 * matplotlib
 * numpy
 * imageio
@@ -30,7 +30,7 @@ The LLFF data loader requires ImageMagick.
 
 You will also need the [LLFF code](http://github.com/fyusion/llff) (and COLMAP) set up to compute poses if you want to run on your own real data.
 
-## What is a NeRF? 
+## What is a NeRF?
 
 A neural radiance field is a simple fully connected network (weights are ~5MB) trained to reproduce input views of a single scene using a rendering loss. The network directly maps from spatial location and viewing direction (5D input) to color and opacity (4D output), acting as the "volume" so we can use volume rendering to differentiably render new views.
 
@@ -46,6 +46,7 @@ Run
 bash download_example_data.sh
 ```
 to get the our synthetic Lego dataset and the LLFF Fern dataset.
+
 To optimize a low-res Fern NeRF:
 ```
 python run_nerf.py --config config_fern.txt