[Submitted on 9 Jun 2014] · arXiv.org

View PDF HTML (experimental)

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.
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:1406.2283 [cs.CV]
  (or arXiv:1406.2283v1 [cs.CV] for this version)
  https://doi.org/10.48550/arXiv.1406.2283

arXiv-issued DOI via DataCite

Submission history

From: David Eigen [view email]
[v1] Mon, 9 Jun 2014 19:01:18 UTC (5,992 KB)

Read the original on arxiv.org ↗