better docs

nerfstudio-project · Oct 5, 2023 · d8ccf28 · d8ccf28
1 parent 9f073ce
commit d8ccf28
Show file tree

Hide file tree

Showing 8 changed files with 37 additions and 203 deletions.
diff --git a/docs/source/_C/cuda.rst b/docs/source/_C/cuda.rst
diff --git a/docs/source/apis/proj.rst b/docs/source/apis/proj.rst
@@ -39,5 +39,4 @@ Citations
     :style: unsrt
     :filter: docname in docnames
 
-.. autoclass:: ProjectGaussians
-    :members:
+.. autoclass:: ProjectGaussians
diff --git a/docs/source/apis/rast.rst b/docs/source/apis/rast.rst
@@ -31,5 +31,4 @@ And
 :math:`σ ∈ R^{2}` is the Mahalanobis distance (here referred to as sigma) which measures how many standard deviations away the center of a gaussian and the rendered pixel center is which is denoted by delta :math:`∆.`
 
 
-.. autoclass:: RasterizeGaussians
-    :members:
+.. autoclass:: RasterizeGaussians
diff --git a/docs/source/apis/utils.rst b/docs/source/apis/utils.rst
@@ -0,0 +1,18 @@
+Utils
+===================================
+In addition to the main projection and rasterization functions, a few CUDA kernel and helper functions are exposed to python with the following bindings:
+
+
+.. currentmodule:: diff_rast
+
+.. autoclass:: BinAndSortGaussians
+
+.. autoclass:: ComputeCov2dBounds
+
+.. autoclass:: GetTileBinEdges
+
+.. autoclass:: SphericalHarmonics
+
+.. autoclass:: MapGaussiansToIntersects
+
+.. autoclass:: ComputeCumulativeIntersects
diff --git a/docs/source/examples/simple_trainer.rst b/docs/source/examples/simple_trainer.rst
@@ -10,7 +10,7 @@ and their differentiability on a single training image. This allows you to overf
 
 Simply run the script with:
 
-.. code-block:: python
+.. code-block:: bash
     :caption: simple_trainer.py
 
     python examples/simple_trainer.py --height 256 --width 256 --num_points 2000 --save_imgs
@@ -23,6 +23,6 @@ to get a result similar to the one below:
 
 You can also provide a path to your own custom image file using the ``--img_path`` flag:
 
-.. code-block:: python
+.. code-block:: bash
 
     python examples/simple_trainer.py --img_path PATH_TO_IMG --save_imgs
diff --git a/docs/source/imgs/training.gif b/docs/source/imgs/training.gif
diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -6,13 +6,19 @@ diff_rast
     :alt: Example training image
 
 Overview
--------------
+--------
 
 *diff_rast* is an open-source library for CUDA accelerated rasterization of gaussians with python bindings. It is inspired by the SIGGRAPH paper "3D Gaussian Splatting for Real-Time Rendering of Radiance Fields" :cite:p:`kerbl3Dgaussians`.
 This libary contains the neccessary components for efficient 3D to 2D projection, sorting, and alpha compositing of gaussians and their associated backward passes for inverse rendering.
 
+Contributing
+------------
+
+This repository was born from the curiosity of people on the Nerfstudio team trying to understand a new rendering technique. We welcome contributions of any kind and are open to feedback, bug-reports, and improvements to help expand the capabilities of this software.
+
+
 Links
-------
+-----
 
 .. toctree::    
    :glob:
@@ -38,21 +44,14 @@ Links
    apis/*
 
 
-.. toctree::    
-   :glob:
-   :maxdepth: 1
-   :caption: Cuda Backend
-
-   _C/*
-
-
 .. toctree::    
    :glob:
    :maxdepth: 1
    :caption: Tests
 
    tests/*
 
+
 Citations
 -------------
 .. bibliography::

diff --git a/docs/source/tests/tests.rst b/docs/source/tests/tests.rst
@@ -1,8 +1,6 @@
 Tests
 ===================================
 
-.. currentmodule:: diff_rast
-
 Testing and verifying CUDA implementations
 --------------------------------------------
 
@@ -11,12 +9,14 @@ They are also ran with any pull-requests into main branch on our github reposito
 
 The tests include: 
 
-.. code-block:: python
+.. code-block:: bash
     :caption: tests/
 
-    ./test_project_gaussians.py
-    ./test_map_gaussians.py
-    ./test_cumulative_intersects.py
+    ./test_bin_and_sort_gaussians.py
     ./test_cov2d_bounds.py
+    ./test_cumulative_intersects.py
+    ./test_get_tile_bin_edges.py
+    ./test_map_gaussians.py
+    ./test_project_gaussians
     ./test_sh.py