UnCommon Objects in 3D
Xingchen Liu, Piyush Tayal, Jianyuan Wang, Jesus Zarzar and, Tom Monnier, Konstantinos Tertikas, Jiali Duan, Antoine Toisoul and, Jason Y. Zhang, Natalia Neverova, Andrea Vedaldi, Roman Shapovalov, and David Novotny

TL;DR
UnCommon Objects in 3D (uCO3D) is a comprehensive, high-quality dataset with diverse 3D object videos and annotations, designed to advance 3D deep learning and generative AI.
Contribution
The paper introduces uCO3D, the largest and most diverse 3D object dataset with extensive annotations, improving training outcomes for 3D models.
Findings
Models trained on uCO3D outperform those trained on other datasets.
uCO3D covers over 1,000 object categories with high-quality annotations.
Enhanced 3D model performance demonstrates dataset's effectiveness.
Abstract
We introduce Uncommon Objects in 3D (uCO3D), a new object-centric dataset for 3D deep learning and 3D generative AI. uCO3D is the largest publicly-available collection of high-resolution videos of objects with 3D annotations that ensures full-360 coverage. uCO3D is significantly more diverse than MVImgNet and CO3Dv2, covering more than 1,000 object categories. It is also of higher quality, due to extensive quality checks of both the collected videos and the 3D annotations. Similar to analogous datasets, uCO3D contains annotations for 3D camera poses, depth maps and sparse point clouds. In addition, each object is equipped with a caption and a 3D Gaussian Splat reconstruction. We train several large 3D models on MVImgNet, CO3Dv2, and uCO3D and obtain superior results using the latter, showing that uCO3D is better for learning applications.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
