Minimal Scene Descriptions from Structure from Motion Models

@article{Cao2014MinimalSD,
  title={Minimal Scene Descriptions from Structure from Motion Models},
  author={Song Cao and Noah Snavely},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={461-468}
}
How much data do we need to describe a location? We explore this question in the context of 3D scene reconstructions created from running structure from motion on large Internet photo collections, where reconstructions can contain many millions of 3D points. We consider several methods for computing much more compact representations of such reconstructions for the task of location recognition, with the goal of maintaining good performance with very small models. In particular, we introduce a… CONTINUE READING
Highly Cited
This paper has 35 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.
25 Citations
17 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 25 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 17 references

3 d point cloud reduction using mixedinteger quadratic programming

  • J. Philbin, M. Isard, J. Sivic
  • CVPR Workshops
  • 2013

Fast image - based localization using direct 2 Dto - 3 D matching

  • B. Leibe T. Sattler, L. Kobbelt
  • 2011

Descriptor learning for efficient retrieval

  • B. Leibe T. Sattler, L. Kobbelt
  • 2010

Similar Papers

Loading similar papers…