SIFT Flow: Dense Correspondence across Different Scenes

@inproceedings{Liu2008SIFTFD,
  title={SIFT Flow: Dense Correspondence across Different Scenes},
  author={Ce Liu and Jenny Yuen and Antonio Torralba and Josef Sivic and William T. Freeman},
  booktitle={ECCV},
  year={2008}
}
While image registration has been studied in different areas of computer vision, aligning images depicting different scenes remains a challenging problem, closer to recognition than to image matching. Analogous to optical flow, where an image is aligned to its temporally adjacent frame, we propose SIFT flow, a method to align an image to its neighbors in a large image collection consisting of a variety of scenes. For a query image, histogram intersection on a bag-of-visual-words representation… CONTINUE READING
BETA

Citations

Publications citing this paper.
SHOWING 1-10 OF 459 CITATIONS

Scene labeling using Kernel Codebook Encoding

  • 2017 25th Signal Processing and Communications Applications Conference (SIU)
  • 2017
VIEW 4 EXCERPTS
HIGHLY INFLUENCED

Scene segmentation and labeling using multi-hypothesis superpixels

  • 2015 23nd Signal Processing and Communications Applications Conference (SIU)
  • 2015
VIEW 6 EXCERPTS
HIGHLY INFLUENCED

Comparative study of interactive seed generation for growcut-based fast 3D MRI segmentation

  • Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference
  • 2012
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Image Retargeting Quality Assessment: A Study of Subjective Scores and Objective Metrics

  • IEEE Journal of Selected Topics in Signal Processing
  • 2012
VIEW 10 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Panic Detection in Human Crowds using Sparse Coding

VIEW 17 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Study of subjective and objective quality assessment of retargeted images

  • 2012 IEEE International Symposium on Circuits and Systems
  • 2012
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Hierarchical fusion of descriptor matching and L-K optical flow

  • 2011 18th IEEE International Conference on Image Processing
  • 2011
VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Copy and Paste: Temporally Consistent Stereoscopic Video Blending

  • IEEE Transactions on Circuits and Systems for Video Technology
  • 2018
VIEW 7 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2009
2019

CITATION STATISTICS

  • 93 Highly Influenced Citations

  • Averaged 28 Citations per year from 2017 through 2019

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…