UnCommon Objects in 3D
This provides a more diverse and higher-quality dataset for 3D deep learning and generative AI, addressing a bottleneck for researchers and practitioners in these fields, though it is incremental as it builds on prior datasets.
The authors tackled the problem of limited diversity and quality in 3D object datasets by introducing uCO3D, a new dataset with over 1,000 object categories and high-resolution videos, and showed that training models on uCO3D yields superior results compared to existing datasets like MVImgNet and CO3Dv2.
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$^{\circ}$ 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.