Add comprehensive README with video descriptions

README.md

@@ -0,0 +1,80 @@
+---
+license: mit
+tags:
+- 3d-gaussian-splatting
+- avatar
+- novel-view-synthesis
+- human-reconstruction
+---
+
+# GUAVA Demo Videos
+
+This repository contains demo videos from [GUAVA: Generalizable Upper Body 3D Gaussian Avatar](https://github.com/Pixel-Talk/GUAVA).
+
+## 📹 Demo Videos
+
+### 1. Self-Reenactment
+**File**: `demo_videos/self_reenactment.mp4` (3.1MB)
+
+Self-reenactment using the same person's video. The model reconstructs a 3D Gaussian avatar and re-renders it from the original viewpoint.
+
+### 2. Cross-Reenactment
+**File**: `demo_videos/cross_reenactment.mp4` (2.0MB)
+
+Cross-reenactment transferring motion and expression from one video to a different person's image. This demonstrates the model's ability to generalize across different identities.
+
+### 3. Dynamic Novel Views (Rotation Only)
+**File**: `demo_videos/dynamic_novel_views_rotation.mp4` (1.7MB)
+
+Dynamic novel view synthesis with camera rotation around the avatar. The camera orbits around the subject while maintaining a fixed distance, showing the 3D consistency of the reconstructed avatar.
+
+### 4. Dynamic Novel Views (Rotation + Zoom) ⭐
+**File**: `demo_videos/dynamic_novel_views_rotation_zoom.mp4` (1.8MB)
+
+**This is the video with both rotation AND zoom!** 
+
+Dynamic novel view synthesis combining:
+- **Camera rotation**: Horizontal and vertical rotation around the avatar
+- **Camera zoom**: Smooth zoom in/out effect (0.7x to 1.3x distance variation)
+
+This demonstrates the full 3D reconstruction quality with both viewpoint changes and distance variations.
+
+## 🎯 Features Demonstrated
+
+| Feature | Self | Cross | Rotation | Rotation+Zoom |
+|---------|------|-------|----------|---------------|
+| Identity preservation | ✅ | ✅ | ✅ | ✅ |
+| Motion transfer | ✅ | ✅ | ✅ | ✅ |
+| Novel viewpoints | ❌ | ❌ | ✅ | ✅ |
+| Distance variation | ❌ | ❌ | ❌ | ✅ |
+
+## 🚀 Technical Details
+
+- **Model**: GUAVA (286.98M parameters)
+- **Input**: Tracked video with SMPL-X and FLAME parameters
+- **Output**: 512x512 rendered frames at 30 FPS
+- **Rendering Speed**: ~6-9 iterations/second on single GPU
+
+## 📖 Citation
+
+If you find this work helpful, please cite:
+
+```bibtex
+@article{GUAVA,
+  title={GUAVA: Generalizable Upper Body 3D Gaussian Avatar},
+  author={Zhang, Dongbin and Liu, Yunfei and Lin, Lijian and Zhu, Ye and Li, Yang and Qin, Minghan and Li, Yu and Wang, Haoqian},
+  journal={arXiv preprint arXiv:2505.03351},
+  year={2025}
+}
+```
+
+## 🔗 Links
+
+- [Project Page](https://eastbeanzhang.github.io/GUAVA/)
+- [Paper](https://arxiv.org/abs/2505.03351)
+- [GitHub](https://github.com/Pixel-Talk/GUAVA)
+- [EHM Tracker](https://github.com/Pixel-Talk/EHM-Tracker/)
+
+## 📝 License
+
+MIT License