Note: we compress these motion pictures for faster previewing.
Examples of text-to-3D content creations with our framework, the *LucidDreamer*, within **~35mins** on A100.
## 🎏 Abstract
We present a text-to-3D generation framework, named the *LucidDreamer*, to distill high-fidelity textures and shapes from pretrained 2D diffusion models.
CLICK for the full abstract
> The recent advancements in text-to-3D generation mark a significant milestone in generative models, unlocking new possibilities for creating imaginative 3D assets across various real-world scenarios. While recent advancements in text-to-3D generation have shown promise, they often fall short in rendering detailed and high-quality 3D models. This problem is especially prevalent as many methods base themselves on Score Distillation Sampling (SDS). This paper identifies a notable deficiency in SDS, that it brings inconsistent and low-quality updating direction for the 3D model, causing the over-smoothing effect. To address this, we propose a novel approach called Interval Score Matching (ISM). ISM employs deterministic diffusing trajectories and utilizes interval-based score matching to counteract over-smoothing. Furthermore, we incorporate 3D Gaussian Splatting into our text-to-3D generation pipeline. Extensive experiments show that our model largely outperforms the state-of-the-art in quality and training efficiency.
## 🔧 Training Instructions
Our code is now released! Please refer to this [**link**](resources/Training_Instructions.md) for detailed training instructions.
## 🚧 Todo
- [x] Release the basic training codes
- [x] Release the guidance documents
- [ ] Release the training codes for more applications
## 📍 Citation
```
@misc{EnVision2023luciddreamer,
title={LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching},
author={Yixun Liang and Xin Yang and Jiantao Lin and Haodong Li and Xiaogang Xu and Yingcong Chen},
year={2023},
eprint={2311.11284},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
## Acknowledgement
This work is built on many amazing research works and open-source projects:
- [gaussian-splatting](https://github.com/graphdeco-inria/gaussian-splatting) and [diff-gaussian-rasterization](https://github.com/graphdeco-inria/diff-gaussian-rasterization)
- [Stable-Dreamfusion](https://github.com/ashawkey/stable-dreamfusion)
- [Point-E](https://github.com/openai/point-e)
Thanks for their excellent work and great contribution to 3D generation area.
Note: we compress these motion pictures for faster previewing.
Examples of text-to-3D content creations with our framework, the *LucidDreamer*, within **~35mins** on A100.