KeystoneDepth

A collection of 37,239 rectified historical stereo image pairs from the Keystone-Mast Collection.

Xuan Luo

University of Washington

Yanmeng Kong

University of Washington

Jason Lawrence

Google Research

Ricardo Martin-Brualla

Google Research

Steven M. Seitz

University of Washington, Google Research

Overview Video


Introduction

Stereo cameras were invented in the 1850s (top-left) and hundreds of thousands of antique stereographs are available today, like this one of Thomas Edison (top-right). We introduce KeystoneDepth, a collection of 37,239 antique stereographs of historical scenes captured between 1864 and 1966 with clean rectified stereo image pairs, disparity maps (bottom), and meta data.


This paper introduces KeystoneDepth, the largest and most diverse collection of rectified historical stereo image pairs to date, consisting of tens of thousands of stereographs of people, events, objects, and scenes recorded between 1864 and 1966. Leveraging the Keystone-Mast Collection of stereographs from the California Museum of Photography, we apply multiple processing steps to produce clean stereo image pairs, complete with calibration data, rectification transforms, and disparity maps. We introduce a novel stereo rectification technique based on the unique properties of antique stereo cameras. To better visualize the results on 2D displays, we also introduce a self-supervised deep view synthesis technique trained on historical imagery.

Click the links below to download the KeystoneDepth collection or explore its content.

Terms of Use

The metadata and the stereographs (zip, drive and in detail pages) in this dataset are in public domain. Everything else including the cropped and rectified images, the disparity maps, the camera calibration parameters (rectification matrices, principal points), etc. along with this website are licensed under a Creative Commons Attribution 4.0 License.

BibTeX

@inproceedings{luo2020keystonedepth,
  title={KeystoneDepth: History in 3D},
  author={Luo, Xuan and Kong, Yanmeng and Lawrence, Jason and Martin-Brualla, Ricardo and Seitz, Steven M.},
  booktitle={International Conference on 3D Vision (3DV)},
  month={November},
  year={2020},
  url={https://http://keystonedepth.cs.washington.edu},
  pages={463-472},
  organization={IEEE}
}

Related Work

X. Luo, Y. Kong, J. Lawrence, R. M. Brualla, S. M. Seitz. Slow Glass: Visualizing History in 3D, Fourth Workshop on Computer Vision for AR/VR, 2020. [pdf] [talk]