This repository contains scripts to download and process Objaverse-XL.
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: π§΅π
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!
![](https://private-user-images.githubusercontent.com/28768645/261399212-43833dd3-ec97-4a3d-8782-00a6aea584b4.jpeg?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjA0NDk0NDQsIm5iZiI6MTcyMDQ0OTE0NCwicGF0aCI6Ii8yODc2ODY0NS8yNjEzOTkyMTItNDM4MzNkZDMtZWM5Ny00YTNkLTg3ODItMDBhNmFlYTU4NGI0LmpwZWc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNzA4JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDcwOFQxNDMyMjRaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT03NjM2M2Y0MDUyYWQ1ZTBlNDliYjhiYzE3ZWU5OGZlZTFlNWUxYjdkZmJhYjA2ODliOTViZmRiZmFhMWYzNTMyJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.2wZ6w7m5Jwviy5HSCXEaVaWa2QC6H4Qhie8WTB5yFOM)
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 π paper :)
![](https://private-user-images.githubusercontent.com/28768645/261399790-8470e4df-e39d-444b-9871-58fbee4b87fd.jpeg?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjA0NDk0NDQsIm5iZiI6MTcyMDQ0OTE0NCwicGF0aCI6Ii8yODc2ODY0NS8yNjEzOTk3OTAtODQ3MGU0ZGYtZTM5ZC00NDRiLTk4NzEtNThmYmVlNGI4N2ZkLmpwZWc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNzA4JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDcwOFQxNDMyMjRaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT01MTNkYWQxMzljYjhjYTA1Mjg1MzZjZDUyZTMxNWZjZTNkMGZkZTViYzIzZjc1N2I4ZTYwZTBjZjkxMzFhYzllJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.otdKTBV2b9QpxY--RFKImlVHXGZ351t4tB0zjm5VSH4)
With the base Zero123-XL foundation model, we can perform image β 3D using DreamFusion, having the model guide a NeRF to generate novel views!
image-to-3d-2.mp4
Text-to-3D comes for free with text β image models, such as with SDXL here, providing the initial image!
text-to-3d-v.mp4
Beyond that, we show strong scaling trends for both Zero123-XL and PixelNeRF!
![](https://private-user-images.githubusercontent.com/28768645/261402910-0c8bb433-27df-43a1-8cb8-1772007c0899.jpeg?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjA0NDk0NDQsIm5iZiI6MTcyMDQ0OTE0NCwicGF0aCI6Ii8yODc2ODY0NS8yNjE0MDI5MTAtMGM4YmI0MzMtMjdkZi00M2ExLThjYjgtMTc3MjAwN2MwODk5LmpwZWc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNzA4JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDcwOFQxNDMyMjRaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT1jNmQ3ZjJkYjQ0YTUyMGJkNzU5ODk5YzNmMDIyOWZkNzBmNDQzMTU4YmEyMjMyNTc4ZDA2ZDFhNGMyNDRlZjEzJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.SuoH1yTq2TcMC4lBLtxXR4os4Lbyvd4k_6npXh56cds)
Check out the Google Colab tutorial to download Objaverse-XL .
Polycam data is available by Polycam to academic researchers for non-commercial use upon request and approval from Polycam. For access please fill out this form.
Blender rendering scripts are available in the scripts/rendering directory!
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.
To cite Objaverse-XL, please cite our π arXiv paper with the following BibTeX entry:
@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 π€Hugging Face at @allenai/objaverse. To cite it, use:
@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}
}