dreamcar123 / README.md
xiaobiaodu's picture
Update README.md
c92e444 verified
---
license: mit
pipeline_tag: image-to-3d
language:
- en
---
## DreamCar: Leveraging Car-specific Prior for in-the-wild 3D Car Reconstruction
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64ad086c5d48838462e2eee1/2MWeSncAOUfhvAw0-VFHz.png)
## ๐Ÿ˜ฎ Highlights
DreamCar can reconstruct a completed 3D car model in the moving-forward scene given a few images even a single image.
### ๐Ÿ”ฅ Symmetry Learning, Car-specific Piror, Pose Optimization
- Symmetry Learning: We use the symmetric nature of cars to reconstruct a completed 3D car.
- Car generative prior: We contribute a 3D car dataset to empower Zero123 with car-specific piror.
- Pose optimization: We propose a pose optimization method to optimize the poses with error from self-driving datasets.
## ๐Ÿšฉ **Updates**
Welcome to **watch** ๐Ÿ‘€ this repository for the latest updates.
โœ… **[2024.7.23]** : Release [project page](https://xiaobiaodu.github.io/dreamcar-project/).
โœ… **[2024.7.23]** : Code Release.
You can find our code in https://github.com/xiaobiaodu/DreamCar