# OccGS

**Repository Path**: kahsolt/occ-gs

## Basic Information

- **Project Name**: OccGS
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: everything
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 1
- **Created**: 2024-04-24
- **Last Updated**: 2024-04-24

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Gaussian Splatting for Unconstrained Captures
<!-- Bernhard Kerbl*, Georgios Kopanas*, Thomas Leimkühler, George Drettakis (* indicates equal contribution)<br>
| [Webpage](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/) | [Full Paper](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/3d_gaussian_splatting_high.pdf) | [Video](https://youtu.be/T_kXY43VZnk) | [Other GRAPHDECO Publications](http://www-sop.inria.fr/reves/publis/gdindex.php) | [FUNGRAPH project page](https://fungraph.inria.fr) |<br>


This repository contains the official authors implementation associated with the paper "3D Gaussian Splatting for Real-Time Radiance Field Rendering", which can be found [here](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/). We further provide the reference images used to create the error metrics reported in the paper, as well as recently created, pre-trained models.  -->

<!-- <a href="https://www.inria.fr/"><img height="100" src="assets/logo_inria.png"> </a>
<a href="https://univ-cotedazur.eu/"><img height="100" src="assets/logo_uca.png"> </a>
<a href="https://www.mpi-inf.mpg.de"><img height="100" src="assets/logo_mpi.png"> </a> 
<a href="https://team.inria.fr/graphdeco/"> <img style="width:100%;" src="assets/logo_graphdeco.png"></a> -->


<!-- 
<section class="section" id="BibTeX">
  <div class="container is-max-desktop content">
    <h2 class="title">BibTeX</h2>
    <pre><code>@Article{kerbl3Dgaussians,
      author       = {Kerbl, Bernhard and Kopanas, Georgios and Leimk{\"u}hler, Thomas and Drettakis, George},
      title        = {3D Gaussian Splatting for Real-Time Radiance Field Rendering},
      journal      = {ACM Transactions on Graphics},
      number       = {4},
      volume       = {42},
      month        = {July},
      year         = {2023},
      url          = {https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/}
}</code></pre>
  </div>
</section> -->


```shell
# HTTPS
git clone https://gitee.com/haiyanggai/gs-w.git
```

## 1、 高斯和编码初始化

$$ {\bf G}_i =  ( {\bf \mu}_i, {\bf f}_i, \alpha_i, {\bf R}_i, {\bf S}_i ) $$ 
$$ {\bf E}_a \in \mathbb R^{n \times 16} $$
$$ {\bf E}_o \in \mathbb R^{n \times 16} $$ 

其中 $ {\bf \mu}_i \in \mathbb R^{3} $， $ {\bf f}_i \in \mathbb R^{32} $， $ \alpha_i \in \mathbb R^{+} $， $ {\bf R}_i \in \mathbb R^{4} $ and $ {\bf S}_i \in \mathbb R^{3} $ 分别是 每个 Gaussian 的均值，位置特征，不透明度，旋转四元数和缩放因子。$ {\bf E}_a $ 和 $ {\bf E}_o $ 是 n 张训练数据对应的外观编码和遮挡编码。

## 2、推理、渲染

颜色 $ \bf c_i \in \mathbb R^3 $ 和遮挡概率 $ o_i \in \mathbb R^{+} $ 从特征和对应编码中解码得到。

$$ {{\bf c}_i} =  \mathbf {MLP_1}({\bf f}_i, \gamma(\bf d), {\bf E}_a^l) $$
$$ {o_i} = \mathbf {MLP_2}({\bf f}_i, \gamma(\bf d), {\bf E}_o^l) $$

通过 $ \mathbf {MLP} $ 的 Gaussian 是经过 insideFrustrum 检查筛选出来的，只需要经过网络一次推理。送入渲染器的 Gaussian 如下：

$$ {\bf G}_i =  ( {\bf \mu}_i, \alpha_i, {\bf R}_i, {\bf S}_i, {\bf c}_i, o_i ) $$ 

渲染器返回 $ \bf C \in \mathbb R^{3 \times H \times W} $ 和 $ \bf O \in \mathbb R^{1 \times H \times W} $.

## 3、监督

先仿照 NeRF-W 建立 baseline

$$ \bf L = \frac {||\bf C - \bf C_{gt} ||_2} {2 \bf O^2} + \frac {log(O)^2}{2} $$