---
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