Update arxiv link

README.md

@@ -1,7 +1,7 @@
 
-# Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation
+# <span style="font-variant: small-caps;">Helvipad</span>: A Real-World Dataset for Omnidirectional Stereo Depth Estimation
 
-[![arXiv](https://img.shields.io/badge/arXiv-2403.16999-b31b1b.svg)](https://arxiv.org/abs/2403.16999)
+[![arXiv](https://img.shields.io/badge/arXiv-2411.18335-b31b1b.svg)](https://arxiv.org/abs/2411.18335)
 [![Dataset](https://img.shields.io/badge/Dataset-Download-blue.svg)](https://github.com/vita-epfl/helvipad/releases)
 [![Project Page](https://img.shields.io/badge/Project-Page-brightgreen)](https://vita-epfl.github.io/Helvipad/)
 
@@ -17,7 +17,7 @@ Collected using two 360° cameras in a top-bottom setup and a LiDAR sensor, the
 depth and disparity labels by projecting 3D point clouds onto equirectangular images. Additionally, we
 provide an augmented training set with a significantly increased label density by using depth completion.
 We benchmark leading stereo depth estimation models for both standard and omnidirectional images.
-Results show that while recent stereo methods perform decently, a significant challenge persists in accurately
+The results show that while recent stereo methods perform decently, a significant challenge persists in accurately
 estimating depth in omnidirectional imaging. To address this, we introduce necessary adaptations to stereo models,
 achieving improved performance.
 

index.html

@@ -79,17 +79,27 @@ <h1 class="title is-1 publication-title">
             <div class="publication-links">
               <!-- PDF Link. -->
               <span class="link-block">
-                <a href="https://arxiv.org/abs/2011.12948"
+                <a href="https://arxiv.org/abs/2411.18335"
                    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>
+              <!-- Code Link. -->
+              <span class="link-block">
+                <a href="https://github.com/vita-epfl/Helvipad"
+                   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>
               <!-- Dataset Link. -->
               <span class="link-block">
-                <a href="https://github.com/google/nerfies/releases/tag/0.1"
+                <a href="https://github.com/vita-epfl/helvipad/releases"
                    class="external-link button is-normal is-rounded is-dark">
                   <span class="icon">
                       <i class="far fa-images"></i>
@@ -137,7 +147,7 @@ <h2 class="title is-3">Abstract</h2>
           </p>
           <p>
             We benchmark leading stereo depth estimation models for both standard and omnidirectional images.
-            Results show that while recent stereo methods perform decently, a significant challenge persists in accurately
+            The results show that while recent stereo methods perform decently, a significant challenge persists in accurately
             estimating depth in omnidirectional imaging. To address this, we introduce necessary adaptations to stereo models,
             achieving improved performance.
           </p>