-
-
-
-## 😮 Highlights
-
-Repaint123 crafts 3D content from a single image, matching 2D generation quality in just ***2 minutes***.
-
-### 🔥 Simple Gaussian Splatting baseline for image-to-3D
-- Coarse stage: Gaussian Splatting optimized with SDS loss by Zero123 for geometry formation.
-- Fine stage: Mesh optimized with MSE loss by Stable Diffusion for texture refinement.
-
-### 💡 View consistency, high quality and fast speed
-- Stable Diffusion for high quality and controllable repainting for reference alignment --> view-consistent high-quality image generation.
-- View-consistent high-quality images with simple MSE loss --> fast high-quality 3D content reconstruction.
-
-
-
-## 🚩 **Updates**
-
-Welcome to **watch** 👀 this repository for the latest updates.
-
-✅ **[2023.12.21]** : We have released our paper, Repaint123 on [arXiv](https://arxiv.org/abs/2312.13271).
-- [ ] [2023.12.21]: Release project page.
-- [ ] Code release.
-- [ ] Online Demo.
-
-
-## 🤗 Demo
-
-Coming soon!
-
-## 🚀 Image-to-3D Results
-
-### Qualitative comparison
-
-
-
-### Quantitative comparison
-
-
-
-
-## 👍 **Acknowledgement**
-This work is built on many amazing research works and open-source projects, thanks a lot to all the authors for sharing!
-* [DreamGaussian](https://github.com/dreamgaussian/dreamgaussian)
-* [ControlNet](https://github.com/lllyasviel/ControlNet)
-* [Repaint](https://github.com/andreas128/RePaint)
-* [Diffusers](https://github.com/huggingface/diffusers)
-
-