Skip to content

Commit

Permalink
Add website
Browse files Browse the repository at this point in the history 
Co-authored-by: muyishen2040 <muyishen2040@gmail.com>
Co-authored-by: AndreaHsu <andrea.843843@gmail.com>
Co-authored-by: Howardkhh <howard.hou.fan@gmail.com>
Co-authored-by: VickyHuang1113 <ychuang1113@gmail.com>
  • Loading branch information
@Howardkhh @muyishen2040
@AndreaHsu @VickyHuang1113 @j3soon
4 people authored and j3soon committed Mar 23, 2024
1 parent 62ed58c commit 1d94a8e
Show file tree
Hide file tree
Showing 122 changed files with 16,281 additions and 0 deletions.
2 changes: 2 additions & 0 deletions .gitignore
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
.DS_store
.idea
35 changes: 35 additions & 0 deletions README.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
# DriveEnv-NeRF: Exploration of A NeRF-Based Autonomous Driving Environment for Real-World Performance Validation

This is the repository that contains source code for the [DriveEnv-NeRF website](https://muyishen2040.github.io/DriveEnvNeRF).

## [Demo Video](https://youtu.be/8wNflV_A5FM)

[![](static/images/video_preview.jpg)](https://youtu.be/8wNflV_A5FM)

## Abstract

In this study, we introduce the DriveEnv-NeRF framework, which leverages Neural Radiance Fields (NeRF) to enable the validation and faithful forecasting of the efficacy of autonomous driving agents in a targeted real-world scene. Standard simulator-based rendering often fails to accurately reflect real-world performance due to the sim-to-real gap, which represents the disparity between virtual simulations and real-world conditions. To mitigate this gap, we propose a workflow for building a high-fidelity simulation environment of the targeted real-world scene using NeRF. This approach is capable of rendering realistic images from novel viewpoints and constructing 3D meshes for emulating collisions. The validation of these capabilities through the comparison of success rates in both simulated and real environments demonstrates the benefits of using DriveNeRF-Env as a real-world performance indicator. Furthermore, the DriveNeRF-Env framework can serve as a training environment for autonomous driving agents under various lighting conditions. This approach enhances the robustness of the agents and reduces performance degradation when deployed to the target real scene, compared to agents fully trained using the standard simulator rendering pipeline.

## Framework Overview

The overview figure presents our proposed framework, DriveEnv-NeRF, which is designed to create highly
realistic 3D simulations of a given environment. Initially, we capture videos of the target scene under
various lighting conditions to ensure a comprehensive representation. These videos are processed to
extract frames and generate camera parameters using structure-from-motion techniques. Following this, a
NeRF model is trained with these inputs to produce novel view renderings and 3D meshes of the scene. These
elements serve as the basis for visual observation and physical interactions within the simulation
environment. Appearance embeddings are incorporated into the NeRF model to enhance the realism and
variability of the environment. With DriveEnv-NeRF developed, the framework allows for the full evaluation
and training of a driving policy within this environment. This framework enables the prediction of
real-world performance and the application of the trained driving policy to real-world scenarios directly.
![Framework Overview](static/images/framework_overview.png)

## Citing DriveEnv-NeRF

> To be Added
## Website License

The template of this website is borrowed from [Nerfies](https://github.com/nerfies/nerfies.github.io)

<a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by-sa/4.0/88x31.png" /></a><br />This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/">Creative Commons Attribution-ShareAlike 4.0 International License</a>.
317 changes: 317 additions & 0 deletions index.html
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,317 @@
<!DOCTYPE html>
<html>

<head>
<meta charset="utf-8">
<meta name="description" content="A NeRF-based autonomous driving environment for real-world performance validation.">
<meta name="keywords" content="DriveEnv-NeRF, RL, NeRF">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>DriveEnv-NeRF: Exploration of A NeRF-Based Autonomous Driving Environment for Real-World Performance Validation
</title>

<link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet">

<link rel="stylesheet" href="./static/css/bulma.min.css">
<link rel="stylesheet" href="./static/mp4/bulma-carousel.min.css">
<link rel="stylesheet" href="./static/css/bulma-slider.min.css">
<link rel="stylesheet" href="./static/css/fontawesome.all.min.css">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
<link rel="stylesheet" href="./static/css/index.css">
<link rel="icon" href="./static/images/favicon.svg">

<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
<script defer src="./static/js/fontawesome.all.min.js"></script>
<script src="./static/js/bulma-carousel.min.js"></script>
<script src="./static/js/bulma-slider.min.js"></script>
<script src="./static/js/index.js"></script>
</head>

<body>
<section class="hero">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title">DriveEnv-NeRF</h1>
<h3 class="publication-title">Exploration of A NeRF-Based Autonomous Driving Environment for
Real-World Performance Validation</h3>
<hr>
<div class="is-size-5 publication-authors">
<span class="author-block">
Mu-Yi Shen<sup>1*</sup>,
</span>
<span class="author-block">
Chia-Chi Hsu<sup>1*</sup>,
</span>
<span class="author-block">
Hao-Yu Hou<sup>1*</sup>,
</span>
<span class="author-block">
Yu-Chen Huang<sup>1*</sup>,
</span>
<span class="author-block">
Wei-Fang Sun<sup>2</sup>,
</span><br>
<span class="author-block">
Chia-Che Chang<sup>3</sup>,
</span>
<span class="author-block">
Yu-Lun Liu<sup>4</sup>,
</span>
<span class="author-block">
Chun-Yi Lee<sup>1</sup>,
</span>
</div>

<div class="is-size-5 publication-authors">
<span class="author-block"><sup>1</sup>Elsa Lab, National Tsing Hua University,</span>
<span class="author-block"><sup>2</sup>NVIDIA AI Technology Center, NVIDIA Corporation,</span>
<span class="author-block"><sup>3</sup>MediaTek Inc.,</span>
<span class="author-block"><sup>4</sup>National Yang Ming Chiao Tung University,</span>
<span class="author-block"><sup>*</sup>Equal Contribution</span>
</div>

<div class="column has-text-centered">
<div class="publication-links">
<!-- PDF Link. -->
<!-- <span class="link-block">
<a href="https://arxiv.org/pdf/2011.12948"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
</span>
<span>Paper</span>
</a>
</span> -->
<span class="link-block">
<!-- TODO: Add link -->
<a href="#" class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="ai ai-arxiv"></i>
</span>
<span>arXiv</span>
</a>
</span>
<!-- Video Link. -->
<span class="link-block">
<a href="https://youtu.be/8wNflV_A5FM"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fab fa-youtube"></i>
</span>
<span>Video</span>
</a>
</span>
<!-- Code Link. -->
<span class="link-block">
<a href="https://github.com/muyishen2040/DriveEnvNeRF"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fab fa-github"></i>
</span>
<span>Code</span>
</a>
</span>
</div>
</div>
</div>
</div>
</section>

<section class="hero teaser">
<!-- Paper video. -->
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Video</h2>
<div class="publication-video">
<iframe src="https://www.youtube.com/embed/8wNflV_A5FM?si=ecMWetW--N-oaoWG" frameborder="0"
allow="autoplay; encrypted-media" allowfullscreen></iframe>
</div>
</div>
</div>
<!--/ Paper video. -->
</section>

<section class="section">
<div class="container is-max-desktop">
<!-- Abstract. -->
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
In this study, we introduce the DriveEnv-NeRF framework, which leverages Neural Radiance Fields (NeRF) to
enable the validation and faithful forecasting of the efficacy of autonomous driving agents in a targeted
real-world scene. Standard simulator-based rendering often fails to accurately reflect real-world
performance due to the sim-to-real gap, which represents the disparity between virtual simulations and
real-world conditions. To mitigate this gap, we propose a workflow for building a high-fidelity simulation
environment of the targeted real-world scene using NeRF. This approach is capable of rendering realistic
images from novel viewpoints and constructing 3D meshes for emulating collisions. The validation of these
capabilities through the comparison of success rates in both simulated and real environments demonstrates
the benefits of using DriveNeRF-Env as a real-world performance indicator. Furthermore, the DriveNeRF-Env
framework can serve as a training environment for autonomous driving agents under various lighting
conditions. This approach enhances the robustness of the agents and reduces performance degradation when
deployed to the target real scene, compared to agents fully trained using the standard simulator rendering
pipeline.
</p>
</div>
</div>
</div>
<!--/ Abstract. -->

</div>
</section>


<section class="section">
<div class="container is-max-desktop">

<div class="container">

<!-- Framework. -->
<div class="content">
<h2 class="title is-3">Framework Overview</h2>
<div class="content has-text-justified">
<p>
The overview figure presents our proposed framework, DriveEnv-NeRF, which is designed to create highly
realistic 3D simulations of a given environment. Initially, we capture videos of the target scene under
various lighting conditions to ensure a comprehensive representation. These videos are processed to
extract frames and generate camera parameters using structure-from-motion techniques. Following this, a
NeRF model is trained with these inputs to produce novel view renderings and 3D meshes of the scene. These
elements serve as the basis for visual observation and physical interactions within the simulation
environment. Appearance embeddings are incorporated into the NeRF model to enhance the realism and
variability of the environment. With DriveEnv-NeRF developed, the framework allows for the full evaluation
and training of a driving policy within this environment. This framework enables the prediction of
real-world performance and the application of the trained driving policy to real-world scenarios directly.
</p>
</div>
<div class="columns">
<div class="column">
<img src="./static/images/framework_overview.png" alt="Framework Overview" style="width:100%">
</div>
</div>
</div>
<!--/ Framework. -->

<!-- Variable Lighting. -->
<div class="content">
<h2 class="title is-3">Variable Lighting</h2>
<div class="content has-text-justified">
<p>
Environments with various illuminations can be created by controlling appearance embedding.
Here are two examples of lighting transformations, which are from day to night and from cloudy to sunny.
</p>
</div>
<div class="columns">
<div class="column">
<video autoplay muted loop playsinline height="100%">
<source src="./static/videos/day2night.mp4" type="video/mp4">
</video>
<p class="has-text-centered">Day → Night</p>
</div>
<div class="column">
<video autoplay muted loop playsinline height="100%">
<source src="./static/videos/cloudy2sunny.mp4" type="video/mp4">
</video>
<p class="has-text-centered">Cloudy → Sunny</p>
</div>
</div>
</div>
<!--/ Variable Lighting. -->

<!-- Appearance Interpolation. -->
<div class="content">
<h2 class="title is-3">Appearance Interpolation</h2>
<div class="content has-text-justified">
<p>
Interpolating between two appearance embeddings can create a transitional lighting.
</p>
</div>
<div class="columns is-vcentered interpolation-panel is-inline-flex">
<div class="column is-2 has-text-centered">
<p style="font-size: 100px;">☀️</p>
</div>
<div class="column interpolation-video-column">
<div id="interpolation-image-wrapper">
Loading...
</div>
<input class="slider is-fullwidth is-large is-info" id="interpolation-slider" step="1" min="0" max="100"
value="50" type="range">
</div>
<div class="column is-2 has-text-centered">
<p style="font-size: 100px;">🌙</p>
</div>
</div>
</div>
<!--/ Appearance Interpolation. -->
<br>

<!-- Sim2Real. -->
<div class="content">
<h2 class="title is-3">Sim2Real</h2>
<div class="content has-text-justified">
<p>
In addition, DriveEnv-NeRF can function as a training environment for RL driving agents with only raw
image inputs.
Training with varying lighting conditions enables the agents to adapt to different real-world scenarios.
These RL agents can be directly deployed to the real-world, maintaining high success rates in the
experiments.
</p>
</div>
<div class="columns">
<div class="column">
<video autoplay muted loop playsinline height="100%">
<source src="./static/videos/sim2real_day.mp4" type="video/mp4">
</video>
<p class="has-text-centered">Day</p>
</div>
<div class="column">
<video autoplay muted loop playsinline height="100%">
<source src="./static/videos/sim2real_night.mp4" type="video/mp4">
</video>
<p class="has-text-centered">Night</p>
</div>
</div>
</div>
<!--/ Sim2Real. -->
</div>
</div>
</section>

<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title">BibTeX</h2>
<blockquote>
(To be Added)
</blockquote>
</div>
</section>


<footer class="footer">
<div class="container">
<div class="columns is-centered">
<div class="column is-8">
<div class="content">
<p>
The template of this page is based on the
<a href="https://github.com/nerfies/nerfies.github.io">Nerfies</a> website.
You are free to borrow the <a href="https://github.com/muyishen2040/DriveEnvNeRF">code</a> of this website,
we just ask that you link back to this page in the footer.
Please remember to remove the analytics code included in the header of the website which
you do not want on your website.
</p>
<p>
This website is licensed under a <a rel="license"
href="http://creativecommons.org/licenses/by-sa/4.0/">Creative
Commons Attribution-ShareAlike 4.0 International License</a>.
</p>
</div>
</div>
</div>
</div>
</footer>

</body>

</html>
Loading

0 comments on commit 1d94a8e

Please sign in to comment.