Depth Map Prediction from a Single Image using a Multi-Scale Deep Network. Eigen, D., Puhrsch, C., & Fergus, R. arXiv:1406.2283 [cs], June, 2014. arXiv: 1406.2283
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network [link]Paper  abstract   bibtex   
Predicting depth is an essential component in understanding the 3D geometry of a scene. While for stereo images local correspondence suffices for estimation, finding depth relations from a single image is less straightforward, requiring integration of both global and local information from various cues. Moreover, the task is inherently ambiguous, with a large source of uncertainty coming from the overall scale. In this paper, we present a new method that addresses this task by employing two deep network stacks: one that makes a coarse global prediction based on the entire image, and another that refines this prediction locally. We also apply a scale-invariant error to help measure depth relations rather than scale. By leveraging the raw datasets as large sources of training data, our method achieves state-of-the-art results on both NYU Depth and KITTI, and matches detailed depth boundaries without the need for superpixelation.
@article{eigen_depth_2014,
	title = {Depth {Map} {Prediction} from a {Single} {Image} using a {Multi}-{Scale} {Deep} {Network}},
	url = {http://arxiv.org/abs/1406.2283},
	abstract = {Predicting depth is an essential component in understanding the 3D geometry of a scene. While for stereo images local correspondence suffices for estimation, finding depth relations from a single image is less straightforward, requiring integration of both global and local information from various cues. Moreover, the task is inherently ambiguous, with a large source of uncertainty coming from the overall scale. In this paper, we present a new method that addresses this task by employing two deep network stacks: one that makes a coarse global prediction based on the entire image, and another that refines this prediction locally. We also apply a scale-invariant error to help measure depth relations rather than scale. By leveraging the raw datasets as large sources of training data, our method achieves state-of-the-art results on both NYU Depth and KITTI, and matches detailed depth boundaries without the need for superpixelation.},
	urldate = {2017-12-28TZ},
	journal = {arXiv:1406.2283 [cs]},
	author = {Eigen, David and Puhrsch, Christian and Fergus, Rob},
	month = jun,
	year = {2014},
	note = {arXiv: 1406.2283},
	keywords = {Computer Science - Computer Vision and Pattern Recognition}
}

Downloads: 0