restructuring LaTeX part 2: new files for content of survey

data_extraction/latex/3dgs_compression_survey.tex

@@ -0,0 +1,90 @@
+\documentclass{article}
+
+% Packages
+\usepackage[utf8]{inputenc} % input encoding
+\usepackage[T1]{fontenc} % font encoding
+\usepackage{amsmath} % math enhancements
+\usepackage{amsfonts} % math fonts
+\usepackage{amssymb} % additional math symbols
+\usepackage{graphicx} % include graphics
+\usepackage{hyperref} % hyperlinks
+\usepackage{cite} % improved citations
+\usepackage{geometry} % page dimensions
+\usepackage{authblk} % for author affiliations
+\usepackage{float}
+\usepackage{booktabs}
+\usepackage{siunitx}
+\usepackage{array}
+\usepackage{varwidth} 
+\usepackage[table]{xcolor}    % loads also »colortbl«
+% colors for table
+\definecolor{lightred}{HTML}{FF9999}
+\definecolor{lightyellow}{HTML}{FFFF99}
+\definecolor{lightorange}{HTML}{FFCC99}
+
+\usepackage{makecell}
+\usepackage{adjustbox}
+% make text the same size even when its bold in a table
+\newsavebox\CBox
+\def\textBF#1{\sbox\CBox{#1}\resizebox{\wd\CBox}{\ht\CBox}{\textbf{#1}}}
+
+% Page dimensions
+\geometry{letterpaper, margin=1in}
+
+% Title, author, and date
+\title{3DGS.zip: A survey on 3D Gaussian Splatting Compression Methods}
+\author[1]{Milena T. Bagdasarian}
+\author[1]{Paul Knoll}
+\author[1,2]{Florian Barthel}
+\author[1]{Anna Hilsmann}
+\author[1,2]{Peter Eisert}
+\author[1]{Wieland Morgenstern}
+
+\affil[1]{Fraunhofer Heinrich Hertz, HHI}
+\affil[2]{Humboldt University of Berlin}
+% make sure no date is displayed, arxiv periodically rebuilds 
+% submissions which would change the date
+\date{}
+
+\begin{document}
+
+\maketitle
+
+\begin{abstract}
+
+    We present a work-in-progress survey on 3D Gaussian Splatting\cite{kerbl3Dgaussians} compression methods, 
+    focusing on their statistical performance across various benchmarks. This survey aims 
+    to facilitate comparability by summarizing key statistics of different compression 
+    approaches in a tabulated format. The datasets evaluated include TanksAndTemples\cite{TanksAndTemples}, 
+    MipNeRF360\cite{MipNeRF360}, DeepBlending\cite{DeepBlending}, and SyntheticNeRF\cite{SyntheticNeRF}. For each method, we report the Peak 
+    Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Learned Perceptual 
+    Image Patch Similarity (LPIPS), and the resultant size in megabytes (MB), as 
+    provided by the respective authors.
+    This is an ongoing, open project, and we invite contributions from the research community 
+    as GitHub issues or pull requests. Please visit \mbox{\bfseries\url{http://w-m.github.io/3dgs-compression-survey/}}
+    for more information and a sortable version of the table.
+
+\end{abstract}
+
+% \section{Introduction}
+% % Novel view synthesis, nerf, 3DGS ..(vs. traditional photogrammetry -> not scalable)
+% % objective: comprehensive overview of the current state of 3DGS compression methods
+% % why is compression important in 3DGS? 
+% % applications in areas such as computer graphics, virtual reality (VR), augmented reality (AR), and real-time rendering.
+
+\section{Scope of this survey}
+% table; comparison of statistics of compression methods
+% types of compression
+% reproducability
+
+In this survey, we focus on compression methods for 3D Gaussian Splatting (3DGS), aiming to optimize memory usage while preserving visual quality and real-time rendering speed. We provide a comprehensive comparison of various compression techniques, with quantitative results for the most commenly used datasets summarized in a tabulated format. Our goal is to ensure transparency and reproducibility of the included approaches. Additionally, we offer a brief explanation of each pipeline and discuss main compression approaches. Rather than covering all existing 3DGS methods, our focus is specifically on their compression techniques; for a broader overview of 3DGS methods and applications, we refer readers to \cite{wu2024recent,fei20243d}. While we include many common approaches shared between neural radiance field (NeRF)\cite{mildenhall2020nerf} compression and 3DGS compression, we direct readers to \cite{li2023compressing,chen2024far} for NeRF-specific compression methods.
+
+\input{3dgs_table}
+
+\input{3dgs_survey_text}
+
+% Bibliography (if needed)
+\bibliographystyle{habbrv}
+\bibliography{../../methods, ../../datasets, survey} % assuming you have a references.bib file
+
+\end{document}

data_extraction/latex/3dgs_survey_text.tex

@@ -0,0 +1,34 @@
+% \section{Datasets and Evaluation Statistics}
+%     % describe all datasets briefly
+%     % describe eval statistics used in the table
+
+% \section{Fundamentals of 3D Gaussian Splatting and Compression}
+
+%     \subsection{3D Gaussian Splatting}
+
+%         3D Gaussian Splatting (3DGS)\cite{kerbl3Dgaussians} is a 3D scene representation based on rasterization used to perform novel view synthesis. While more traditonal methods rely on polygonal meshes or voxel grids, 3D Gaussian Splatting relys on a set of overlapping Gaussian functions (or "splats") to model the appearence of surfaces or volumes in 3D space. A "splat" in 3DGS is a 3D Gaussian ditribution that is described by its position (XYZ), Covariance (stretch and scale), color (RGB) and Alpha (transparency). 
+%         % 3D Gaussian Splatting; basic principles; usage in 3D graphics and rendering.
+%         % Data representation in 3DGS; Gaussian splats; challanges such as data size and rendering performance
+%         % explain need for compression; storage efficiency; computation efficiency
+
+%     \section{Compression in the context of 3D Gaussian Splatting}
+%         % What can be compressed? What do we call compression?
+%         % spatial data, color and intensity, (temporal data - not focused on)
+%         % densification and pruning 
+
+% \section{Classification of Compression Methods}
+%     % Vector quantization
+%     % Anchor-based approaches
+%     % Pruning 
+%     % ... ???
+
+\section{Description of Included Compression Approaches}
+    \input{3dgs_contributions.tex}
+    % contribution summaries from table 
+    % possibly use color encoding
+
+% \section{Discussion}
+
+% \section{Future Directions}
+
+% \section{Conclusion}

data_extraction/latex/build_latex.py

@@ -288,6 +288,8 @@ def cp_images(src_folder, dst_folder):
         "3dgs_compression_survey.blg",
         "3dgs_compression_survey.log",
         "3dgs_compression_survey.out",
+        "3dgs_contributions.tex",
+        "3dgs_table.aux",
         "dataset.bib",
         "methods.bib",
     ]