revert title

envgs/index.html

@@ -140,7 +140,7 @@ <h1 class="title is-1 publication-title">
   <section class="section">
     <div class="container is-max-desktop">
       <!-- Abstract. -->
-      <h2 class="title is-3">Abstract</h2>
+      <h2 class="title is-4">Abstract</h2>
       <div class="content has-text-justified">
           <p>
             Reconstructing complex reflections in real-world scenes from 2D images is essential for achieving photorealistic novel view synthesis. Existing methods that utilize environment maps to model reflections from distant lighting often struggle with high-frequency reflection details and fail to account for near-field reflections. In this work, we introduce EnvGS, a novel approach that employs a set of Gaussian primitives as an explicit 3D representation for capturing reflections of environments. These environment Gaussian primitives are incorporated with base Gaussian primitives to model the appearance of the whole scene. To efficiently render these environment Gaussian primitives, we developed a ray-tracing-based renderer that leverages the GPU's RT core for fast rendering. This allows us to jointly optimize our model for high-quality reconstruction while maintaining real-time rendering speeds. Results from multiple real-world and synthetic datasets demonstrate that our method produces significantly more detailed reflections, achieving the best rendering quality in real-time novel view synthesis.
@@ -153,7 +153,7 @@ <h2 class="title is-3">Abstract</h2>
   <section class="section">
     <div class="container is-max-desktop">
       <!-- Pipeline. -->
-      <h2 class="title is-3">Method</h2>
+      <h2 class="title is-4">Method</h2>
       <img src="static/img/pipeline.png">
       <div class="content has-text-justified">
           <p>
@@ -166,7 +166,7 @@ <h2 class="title is-3">Method</h2>
 
   <section class="section">
     <div class="container is-max-desktop">
-      <h2 class="title is-3">Results and Comparisons</h2>
+      <h2 class="title is-4">Results and Comparisons</h2>
       <p>
         Here we demostrate side-by-side videos comparing our method to top-performing baselines across different captured scenes. <br><br>
         Select a scene and a baseline method below:
@@ -510,7 +510,7 @@ <h2 class="title is-3">Results and Comparisons</h2>
 
  <section class="section">
     <div class="container is-max-desktop">
-      <h2 class="title is-3">Ablation Studies</h2>
+      <h2 class="title is-4">Ablation Studies</h2>
       <p>
         Here we demostrate side-by-side videos comparing our full method to versions of our method where key components have been ablated on the scene gardenspheres. See more details in the paper.<br><br>
         Select an ablation below:
@@ -626,7 +626,7 @@ <h2 class="title is-3">Ablation Studies</h2>
 
   <section class="section">
     <div class="container is-max-desktop">
-      <h2 class="title is-3"> Related Works</h2>
+      <h2 class="title is-4"> Related Works</h2>
       <p>
         <li><a href="https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/">3D Gaussian Splatting for Real-Time Radiance Field Rendering</a></li>
         <li><a href="https://surfsplatting.github.io/">2D Gaussian Splatting for Geometrically Accurate Radiance Fields</a></li>
@@ -641,7 +641,7 @@ <h2 class="title is-3"> Related Works</h2>
 
   <section class="section" id="BibTeX">
     <div class="container is-max-desktop">
-    <h2 class="title is-3">Citation</h2>
+    <h2 class="title is-4">Citation</h2>
     <pre><code>
 @misc{xie2024envgsmodelingviewdependentappearance,
     title={EnvGS: Modeling View-Dependent Appearance with Environment Gaussian},