# 🪐 Objaverse-XL
This repository contains scripts to download and process Objaverse-XL.
<img src="https://mattdeitke.com/static/1cdcdb2ef7033e177ca9ae2975a9b451/9c1ca/objaverse-xl.webp">
Objaverse-XL is an open dataset of over 10 million 3D objects!
With it, we train Zero123-XL, a foundation model for 3D, observing incredible 3D generalization abilities: 🧵👇
## Scale Comparison
Objaverse 1.0 was released back in December. It was a step in the right direction, but still relatively small with 800K objects.
Objaverse-XL is over an order of magnitude larger and much more diverse!
<img src="https://github.com/allenai/objaverse-rendering/assets/28768645/43833dd3-ec97-4a3d-8782-00a6aea584b4">
## Unlocking Generalization
Compared to the original Zero123 model, Zero123-XL improves remarkably in 0-shot generalization abilities, even being able to perform novel view synthesis on sketches, cartoons, and people!
A ton more examples in the [📝 paper](https://arxiv.org/abs/2307.05663) :)
<img src="https://github.com/allenai/objaverse-rendering/assets/28768645/8470e4df-e39d-444b-9871-58fbee4b87fd">
## Image → 3D
With the base Zero123-XL foundation model, we can perform image → 3D using [DreamFusion](https://dreamfusion3d.github.io/), having the model guide a NeRF to generate novel views!
https://github.com/allenai/objaverse-rendering/assets/28768645/571852cd-dc02-46ce-b2bb-88f64a67d0ac
## Text → 3D
Text-to-3D comes for free with text → image models, such as with SDXL here, providing the initial image!
https://github.com/allenai/objaverse-rendering/assets/28768645/96255b42-8158-4c7a-8308-7b0f1257ada8
## Scaling Trends
Beyond that, we show strong scaling trends for both Zero123-XL and [PixelNeRF](https://alexyu.net/pixelnerf/)!
<img src="https://github.com/allenai/objaverse-rendering/assets/28768645/0c8bb433-27df-43a1-8cb8-1772007c0899">
## Tutorial
Check out the [Google Colab tutorial](//colab.research.google.com/drive/1zd4ri7ie_i5TYSUA9xHARh5W8nzrYpwg?usp=sharing) to download Objaverse-XL (work in progress).
## Blender Rendering
Blender rendering scripts are available in the [scripts/rendering directory](https://github.com/allenai/objaverse-xl/tree/main/scripts/rendering)!
## License
The use of the dataset as a whole is licensed under the ODC-By v1.0 license. Individual objects in Objaverse-XL are licensed under different licenses.
## Citation
To cite Objaverse-XL, please cite our [📝 arXiv](https://arxiv.org/abs/2307.05663) paper with the following BibTeX entry:
```bibtex
@article{objaverseXL,
title={Objaverse-XL: A Universe of 10M+ 3D Objects},
author={Matt Deitke and Ruoshi Liu and Matthew Wallingford and Huong Ngo and
Oscar Michel and Aditya Kusupati and Alan Fan and Christian Laforte and
Vikram Voleti and Samir Yitzhak Gadre and Eli VanderBilt and
Aniruddha Kembhavi and Carl Vondrick and Georgia Gkioxari and
Kiana Ehsani and Ludwig Schmidt and Ali Farhadi},
journal={arXiv preprint arXiv:2307.05663},
year={2023}
}
```
Objaverse 1.0 is available on 🤗Hugging Face at [@allenai/objaverse](https://huggingface.co/datasets/allenai/objaverse). To cite it, use:
```bibtex
@article{objaverse,
title={Objaverse: A Universe of Annotated 3D Objects},
author={Matt Deitke and Dustin Schwenk and Jordi Salvador and Luca Weihs and
Oscar Michel and Eli VanderBilt and Ludwig Schmidt and
Kiana Ehsani and Aniruddha Kembhavi and Ali Farhadi},
journal={arXiv preprint arXiv:2212.08051},
year={2022}
}
```
Raw data
{
"_id": null,
"home_page": "https://huggingface.co/datasets/allenai/objaverse-xl",
"name": "objaverse-xl",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "",
"author": "Allen Institute for AI",
"author_email": "mattd@allenai.org",
"download_url": "https://files.pythonhosted.org/packages/ce/3b/b51b1fcd80dfe47372c1b11aa3b4ffc460e47e71229af899e76e4db323f6/objaverse_xl-0.1.3.tar.gz",
"platform": null,
"description": "# \ud83e\ude90 Objaverse-XL\n\nThis repository contains scripts to download and process Objaverse-XL.\n\n<img src=\"https://mattdeitke.com/static/1cdcdb2ef7033e177ca9ae2975a9b451/9c1ca/objaverse-xl.webp\">\n\nObjaverse-XL is an open dataset of over 10 million 3D objects!\n\nWith it, we train Zero123-XL, a foundation model for 3D, observing incredible 3D generalization abilities: \ud83e\uddf5\ud83d\udc47\n\n## Scale Comparison\n\nObjaverse 1.0 was released back in December. It was a step in the right direction, but still relatively small with 800K objects.\n\nObjaverse-XL is over an order of magnitude larger and much more diverse!\n\n<img src=\"https://github.com/allenai/objaverse-rendering/assets/28768645/43833dd3-ec97-4a3d-8782-00a6aea584b4\">\n\n## Unlocking Generalization\n\nCompared to the original Zero123 model, Zero123-XL improves remarkably in 0-shot generalization abilities, even being able to perform novel view synthesis on sketches, cartoons, and people!\n\nA ton more examples in the [\ud83d\udcdd paper](https://arxiv.org/abs/2307.05663) :)\n\n<img src=\"https://github.com/allenai/objaverse-rendering/assets/28768645/8470e4df-e39d-444b-9871-58fbee4b87fd\">\n\n## Image \u2192 3D\n\nWith the base Zero123-XL foundation model, we can perform image \u2192 3D using [DreamFusion](https://dreamfusion3d.github.io/), having the model guide a NeRF to generate novel views!\n\nhttps://github.com/allenai/objaverse-rendering/assets/28768645/571852cd-dc02-46ce-b2bb-88f64a67d0ac\n\n## Text \u2192 3D\n\nText-to-3D comes for free with text \u2192 image models, such as with SDXL here, providing the initial image!\n\nhttps://github.com/allenai/objaverse-rendering/assets/28768645/96255b42-8158-4c7a-8308-7b0f1257ada8\n\n## Scaling Trends\n\nBeyond that, we show strong scaling trends for both Zero123-XL and [PixelNeRF](https://alexyu.net/pixelnerf/)!\n\n<img src=\"https://github.com/allenai/objaverse-rendering/assets/28768645/0c8bb433-27df-43a1-8cb8-1772007c0899\">\n\n## Tutorial\n\nCheck out the [Google Colab tutorial](//colab.research.google.com/drive/1zd4ri7ie_i5TYSUA9xHARh5W8nzrYpwg?usp=sharing) to download Objaverse-XL (work in progress).\n\n## Blender Rendering\n\nBlender rendering scripts are available in the [scripts/rendering directory](https://github.com/allenai/objaverse-xl/tree/main/scripts/rendering)!\n\n\n\n## License\n\nThe use of the dataset as a whole is licensed under the ODC-By v1.0 license. Individual objects in Objaverse-XL are licensed under different licenses.\n\n## Citation\n\nTo cite Objaverse-XL, please cite our [\ud83d\udcdd arXiv](https://arxiv.org/abs/2307.05663) paper with the following BibTeX entry:\n\n```bibtex\n@article{objaverseXL,\n title={Objaverse-XL: A Universe of 10M+ 3D Objects},\n author={Matt Deitke and Ruoshi Liu and Matthew Wallingford and Huong Ngo and\n Oscar Michel and Aditya Kusupati and Alan Fan and Christian Laforte and\n Vikram Voleti and Samir Yitzhak Gadre and Eli VanderBilt and\n Aniruddha Kembhavi and Carl Vondrick and Georgia Gkioxari and\n Kiana Ehsani and Ludwig Schmidt and Ali Farhadi},\n journal={arXiv preprint arXiv:2307.05663},\n year={2023}\n}\n```\n\nObjaverse 1.0 is available on \ud83e\udd17Hugging Face at [@allenai/objaverse](https://huggingface.co/datasets/allenai/objaverse). To cite it, use:\n\n```bibtex\n@article{objaverse,\n title={Objaverse: A Universe of Annotated 3D Objects},\n author={Matt Deitke and Dustin Schwenk and Jordi Salvador and Luca Weihs and\n Oscar Michel and Eli VanderBilt and Ludwig Schmidt and\n Kiana Ehsani and Aniruddha Kembhavi and Ali Farhadi},\n journal={arXiv preprint arXiv:2212.08051},\n year={2022}\n}\n```\n\n\n\n",
"bugtrack_url": null,
"license": "",
"summary": "Objaverse-XL is an open dataset of over 10 million 3D objects",
"version": "0.1.3",
"project_urls": {
"Homepage": "https://huggingface.co/datasets/allenai/objaverse-xl"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "8030867f9d564ac73bf50020ac18618a6a4a7f455059af836b1c78e59c863004",
"md5": "283f7997210acd822199bf427255227b",
"sha256": "95fe14242dc17dfb0310a8cb664d6d85cca8f8b2ca58c7c39fb8203db34513bd"
},
"downloads": -1,
"filename": "objaverse_xl-0.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "283f7997210acd822199bf427255227b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 29800,
"upload_time": "2023-09-18T03:28:21",
"upload_time_iso_8601": "2023-09-18T03:28:21.740728Z",
"url": "https://files.pythonhosted.org/packages/80/30/867f9d564ac73bf50020ac18618a6a4a7f455059af836b1c78e59c863004/objaverse_xl-0.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "ce3bb51b1fcd80dfe47372c1b11aa3b4ffc460e47e71229af899e76e4db323f6",
"md5": "f6cf5619fe140ee436b3b2cbae4b129d",
"sha256": "d7fec7d7f13d3d4aa75d17be46f0074a596d11b9e49129aa720d6154318baaa3"
},
"downloads": -1,
"filename": "objaverse_xl-0.1.3.tar.gz",
"has_sig": false,
"md5_digest": "f6cf5619fe140ee436b3b2cbae4b129d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 22562,
"upload_time": "2023-09-18T03:28:23",
"upload_time_iso_8601": "2023-09-18T03:28:23.533986Z",
"url": "https://files.pythonhosted.org/packages/ce/3b/b51b1fcd80dfe47372c1b11aa3b4ffc460e47e71229af899e76e4db323f6/objaverse_xl-0.1.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-09-18 03:28:23",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "objaverse-xl"
}
JSON