ML Anthology

Photo Uncrop

Qi Shan, Brian Curless, Yasutaka Furukawa, Carlos Hernández, Steven M. Seitz
ECCV 2014 pp. 16-31
doi:10.1007/978-3-319-10599-4_2 /eccv/2014/shan2014eccv-photo/

Abstract

We address the problem of extending the field of view of a photo—an operation we call uncrop . Given a reference photograph to be uncropped, our approach selects, reprojects, and composites a subset of Internet imagery taken near the reference into a larger image around the reference using the underlying scene geometry. The proposed Markov Random Field based approach is capable of handling large Internet photo collections with arbitrary viewpoints, dramatic appearance variation, and complicated scene layout. We show results that are visually compelling on a wide range of real-world landmarks.

PDF ECCV Semantic Scholar

Cite

Text

Shan et al. "Photo Uncrop." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-10599-4_2

Markdown

[Shan et al. "Photo Uncrop." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/shan2014eccv-photo/) doi:10.1007/978-3-319-10599-4_2

BibTeX

@inproceedings{shan2014eccv-photo,
  title     = {{Photo Uncrop}},
  author    = {Shan, Qi and Curless, Brian and Furukawa, Yasutaka and Hernández, Carlos and Seitz, Steven M.},
  booktitle = {European Conference on Computer Vision},
  year      = {2014},
  pages     = {16-31},
  doi       = {10.1007/978-3-319-10599-4_2},
  url       = {https://mlanthology.org/eccv/2014/shan2014eccv-photo/}
}