ObjectNet3D: A Large Scale Database for 3D Object Recognition
Abstract
We contribute a large scale database for 3D object recognition, named ObjectNet3D, that consists of 100 categories, 90,127 images, 201,888 objects in these images and 44,147 3D shapes. Objects in the 2D images in our database are aligned with the 3D shapes, and the alignment provides both accurate 3D pose annotation and the closest 3D shape annotation for each 2D object. Consequently, our database is useful for recognizing the 3D pose and 3D shape of objects from 2D images. We also provide baseline experiments on four tasks: region proposal generation, 2D object detection, joint 2D detection and 3D object pose estimation, and image-based 3D shape retrieval, which can serve as baselines for future research using our database. Our database is available online at http://cvgl.stanford.edu/projects/objectnet3d .
Cite
Text
Xiang et al. "ObjectNet3D: A Large Scale Database for 3D Object Recognition." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-46484-8_10Markdown
[Xiang et al. "ObjectNet3D: A Large Scale Database for 3D Object Recognition." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/xiang2016eccv-objectnet/) doi:10.1007/978-3-319-46484-8_10BibTeX
@inproceedings{xiang2016eccv-objectnet,
title = {{ObjectNet3D: A Large Scale Database for 3D Object Recognition}},
author = {Xiang, Yu and Kim, Wonhui and Chen, Wei and Ji, Jingwei and Choy, Christopher B. and Su, Hao and Mottaghi, Roozbeh and Guibas, Leonidas J. and Savarese, Silvio},
booktitle = {European Conference on Computer Vision},
year = {2016},
pages = {160-176},
doi = {10.1007/978-3-319-46484-8_10},
url = {https://mlanthology.org/eccv/2016/xiang2016eccv-objectnet/}
}