modify gh-page

index.html

@@ -133,8 +133,8 @@ <h1 class="title is-1 publication-title">OASim: an Open and Adaptive Simulator b
           </video>
         </center>
           <h2 class="subtitle has-text-centered">
-            OASim focuses on generating new and highly customizable autonomous driving data through neural implicit 
-            reconstruction and rendering techniques. This technology has a wealth of applications, such as large-scale data and scene generation, corner case generation, autonomous driving closed-loop training, autonomous driving stack testing, etc.
+            OASim focuses on generating new and highly customizable autonomous driving data through neural implicit reconstruction and rendering techniques. 
+            This technology has a wealth of applications, such as large-scale data and scene generation, corner case generation, autonomous driving closed-loop training, autonomous driving stack testing, etc.
           </h2>
       </div>
     </div>
@@ -153,8 +153,11 @@ <h2 class="title is-3">Abstract</h2>
           <div class="content has-text-justified">
             <p>
               <b>
-                With deep learning and computer vision technology development, autonomous driving provides new solutions to improve traffic safety and efficiency. The importance of building high-quality datasets is self-evident, especially with the rise of end-to-end autonomous driving algorithms in recent years. Data plays a core role in the algorithm closed-loop system. However, collecting real world data is expensive, time-consuming, and unsafe. With the development of implicit rendering technology and in-depth research on how to use generative models to produce data at scale, we propose OASim, an autonomous driving data generator based on neural implicit rendering and reconstruction for highly customized data generation. 
-                It has the following characteristics: (1) High-quality scene reconstruction through neural implicit surface reconstruction technology. (2) Trajectory editing of the ego vehicle and participating vehicles. (3) Rich vehicle model library that can be freely selected and inserted to the scene. (4) Rich sensors model library where you can select specified sensors to generate data. (5) A highly customizable data generation system can generate data according to user needs. We demonstrate the high quality and fidelity of the generated data through perception performance evaluation on the Carla simulator and real-world data acquisition.
+                With deep learning and computer vision technology development, autonomous driving provides new solutions to improve traffic safety and efficiency. 
+                The importance of building high-quality datasets is self-evident, especially with the rise of end-to-end autonomous driving algorithms in recent years. 
+                Data plays a core role in the algorithm closed-loop system. However, collecting real-world data is expensive, time-consuming, and unsafe. With the development of implicit rendering technology and in-depth research on using generative models to produce data at scale, we propose OASim, an open and adaptive simulator and autonomous driving data generator based on implicit neural rendering. 
+                It has the following characteristics: (1) High-quality scene reconstruction through neural implicit surface reconstruction technology. (2) Trajectory editing of the ego vehicle and participating vehicles. (3) Rich vehicle model library that can be freely selected and inserted into the scene. 
+                (4) Rich sensors model library where you can select specified sensors to generate data. (5) A highly customizable data generation system can generate data according to user needs. We demonstrate the high quality and fidelity of the generated data through perception performance evaluation on the Carla simulator and real-world data acquisition.
               </b>
             </p>
           </div>
@@ -210,22 +213,6 @@ <h2 class="subtitle has-text-centered">
     </div>
   </section>
 
-  <section class="hero teaser">
-    <div class="container is-max-desktop">
-      <h2 class="title">3D Preview</h2>
-      <div class="hero-body">
-        <center>
-          <video poster="" id="tree" autoplay controls muted loop height="100%" width="80%">
-            <!-- Your video here -->
-            <source src="static/videos/3d_preview.mp4" type="video/mp4">
-          </video>
-        </center>
-          <h2 class="subtitle has-text-centered">
-            OASim can preview the results of 3D implicit reconstruction in real time through the keyboard, and also supports conversion to 3D mesh for preview.
-          </h2>
-      </div>
-    </div>
-  </section>
 
   <!--BibTex citation -->
   <section class="section" id="BibTeX">