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.
@article{arxiv.1804.04610,
title = {Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling},
author = {Xingyuan Sun and Jiajun Wu and Xiuming Zhang and Zhoutong Zhang and Chengkai Zhang and Tianfan Xue and Joshua B. Tenenbaum and William T. Freeman},
journal= {arXiv preprint arXiv:1804.04610},
year = {2018}
}
Comments
CVPR 2018. The first two authors contributed equally to this work. Project page: http://pix3d.csail.mit.edu