+ ddim results

index.html

@@ -590,7 +590,7 @@ pre {
 
     <section id="more_results">
         <hr> 
-        <h2>Applications</h2>  
+        <h2>More Results</h2>  
         <h3>Interpolation </h3> 
             <div class="flex-row">
                 <p>LION can interpolate two shapes by traversing the latent space. The generated shapes are clean and semantically plausible along the entire interpolation path.  </p>
@@ -616,7 +616,26 @@ pre {
             </figure>
            </center>
         <br>
-       
+        <h3>Fast Sampling with DDIM </h3>  
+            <div class="flex-row">
+                <p>The sampling time of LION can be reduced by applying DDIM sampler. 
+                DDIM sampler with 25 steps can already generate high-quality shapes, which takes less than 1 sec. </p>
+            </div>
+            <center>
+            <figure style="width: 100%;">
+                    <a>
+                        <img width="100%" src="assets/ddim_sample.png">
+                    </a>
+                    <p class="caption" style="margin-bottom: 24px;">
+                        DDIM samples from LION trained on different data. The top two rows show the number of steps and the wall-clock time used when drawing one sample. 
+                        With DDIM sampling, we can reduce the sampling time from 27.09 sec (1000 steps) to less than 1 sec (25 steps) to generate an object. 
+                    </p>
+            </figure>
+            </center>
+
+        <br>
+
+      
         <h3>Voxel-Conditioned Synthesis </h3>  
             <div class="flex-row">
                 <p>Given a coarse voxel grid, LION can generate different plausible detailed shapes. </p>