Update README.md

README.md

@@ -12,12 +12,38 @@ tags:
 pipeline_tag: image-to-image
 ---
 
-# RelightFormer: Feed-Forward Generative Transformer for Multi-View Object Relighting
+<p align="center">
+  <svg width="100%" height="100" viewBox="0 0 1000 100" xmlns="http://www.w3.org/2000/svg">
+    <defs>
+      <linearGradient id="gradientText" x1="0%" y1="0%" x2="100%" y2="0%">
+        <stop offset="0%" style="stop-color:#00c6ff;stop-opacity:1" />
+        <stop offset="50%" style="stop-color:#9d50bb;stop-opacity:1" />
+        <stop offset="100%" style="stop-color:#ff00cc;stop-opacity:1" />
+      </linearGradient>
+    </defs>
+    <text x="50%" y="55%" font-family="Arial, sans-serif" font-size="75" font-weight="900" fill="url(#gradientText)" text-anchor="middle" dominant-baseline="middle" letter-spacing="2">RelightFormer</text>
+  </svg>
+</p>
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/vLAR-group/RelightFormer/main/demo/teaser.jpg" alt="Teaser" width="80%">
+</p>
+
+<p align="center">
+  <strong>vLAR Group</strong> | <em>SIGGRAPH Asia 2026</em>
+</p>
+
+<p align="center">
+  <a href="https://github.com/vLAR-group/RelightFormer">
+    <img src="https://img.shields.io/badge/Code-GitHub-black" alt="Code">
+  </a>
+  <a href="https://huggingface.co/datasets/vLAR/LavalObjaverseDataset">
+    <img src="https://img.shields.io/badge/Dataset-Hugging%20Face-yellow" alt="Dataset">
+  </a>
+</p>
 
 <p align="center">
-  <strong>SIGGRAPH Asia 2026</strong> | 
-  <a href="https://github.com/vLAR-group/RelightFormer">🌐 GitHub Repository</a> | 
-  <a href="https://huggingface.co/datasets/vLAR/LavalObjaverseDataset">🤗 Dataset</a>
+  <strong>A large-scale, high-quality dataset for multi-view relighting.</strong>
 </p>
 
 ## 🌟 Overview