Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
Abstract
We study 3D shape modeling from a single image and make contributions to it in three aspects. First, we present Pix3D, a large-scale benchmark of diverse image-shape pairs with pixel-level 2D-3D alignment. Pix3D has wide applications in shape-related tasks including reconstruction, retrieval, viewpoint estimation, etc. Building such a large-scale dataset, however, is highly challenging; existing datasets either contain only synthetic data, or lack precise alignment between 2D images and 3D shapes, or only have a small number of images. Second, we calibrate the evaluation criteria for 3D shape reconstruction through behavioral studies, and use them to objectively and systematically benchmark cutting-edge reconstruction algorithms on Pix3D. Third, we design a novel model that simultaneously performs 3D reconstruction and pose estimation; our multi-task learning approach achieves state-of-the-art performance on both tasks.
Cite
Text
Sun et al. "Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00314Markdown
[Sun et al. "Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/sun2018cvpr-pix3d/) doi:10.1109/CVPR.2018.00314BibTeX
@inproceedings{sun2018cvpr-pix3d,
title = {{Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling}},
author = {Sun, Xingyuan and Wu, Jiajun and Zhang, Xiuming and Zhang, Zhoutong and Zhang, Chengkai and Xue, Tianfan and Tenenbaum, Joshua B. and Freeman, William T.},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2018},
doi = {10.1109/CVPR.2018.00314},
url = {https://mlanthology.org/cvpr/2018/sun2018cvpr-pix3d/}
}