update info

Author: arthur-qiu

index.html

@@ -72,7 +72,7 @@ <h2><b>Methodology</b></h2>
 
 
 <div class="content">
-  <h2><b>T2V Ablation (960 × 1664)</b></h2>
+  <h2><b>Text-to-Video Ablation (960 × 1664)</b></h2>
   <p>Although all variants can generate rough results. Our full method performs the best.</p>
   <div style="text-align: center;">
   <video width="1000" autoplay muted loop playsinline>
@@ -86,7 +86,7 @@ <h2><b>T2V Ablation (960 × 1664)</b></h2>
 
 
 <div class="content">
-  <h2><b>T2V Comparison (960 × 1664)</b></h2>
+  <h2><b>Text-to-Video Comparison (960 × 1664)</b></h2>
   <p>Although other baselines can produce reasonable results at moderately higher resolutions, they still suffer from varying degrees of blurriness. In contrast, CineScale generates high-quality videos with rich visual details.</p>
   <div style="text-align: center;">
   <video width="1000" autoplay muted loop playsinline>
@@ -100,7 +100,7 @@ <h2><b>T2V Comparison (960 × 1664)</b></h2>
 
 
 <div class="content">
-  <h2><b>T2V Comparison (1920 × 3328)</b></h2>
+  <h2><b>Text-to-Video Comparison (1920 × 3328)</b></h2>
   <p>Image qualitative comparisons with other baselines. At the resolution several times higher than those used during training, LTX and Wan-DI tend to fail completely. While UAV, a video super-resolution approach, can still produce visually reasonable results, it is unable to recover fine details that are ambiguous or missing in the low-resolution inputs. In contrast, CineScale consistently generates high-quality videos with rich and faithful visual details.</p>
   <div style="text-align: center;">
   <video width="1000" autoplay muted loop playsinline>