Accurate Optical Flow via Direct Cost Volume Processing

@article{Xu2017AccurateOF,
  title={Accurate Optical Flow via Direct Cost Volume Processing},
  author={Jia Xu and Ren{\'e} Ranftl and Vladlen Koltun},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={5807-5815}
}
We present an optical flow estimation approach that operates on the full four-dimensional cost volume. This direct approach shares the structural benefits of leading stereo matching pipelines, which are known to yield high accuracy. To this day, such approaches have been considered impractical due to the size of the cost volume. We show that the full four-dimensional cost volume can be constructed in a fraction of a second due to its regularity. We then exploit this regularity further by… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 64 CITATIONS

Occlusion Aware Unsupervised Learning of Optical Flow

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2017
VIEW 15 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Creative Flow+ Dataset

VIEW 9 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

KalmanFlow 2.0: Efficient Video Optical Flow Estimation via Context-Aware Kalman Filtering

  • IEEE Transactions on Image Processing
  • 2019
VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Sparse Data Interpolation Using the Geodesic Distance Affinity Space

  • IEEE Signal Processing Letters
  • 2019
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation

  • IEEE transactions on pattern analysis and machine intelligence
  • 2018
VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Saliency guided fast interpolation for large displacement optical flow

  • 2018 24th International Conference on Pattern Recognition (ICPR)
  • 2018
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2017
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Model-based Optical Flow: Layers, Learning, and Geometry

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2019

CITATION STATISTICS

  • 10 Highly Influenced Citations

  • Averaged 21 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 38 REFERENCES

Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 10 EXCERPTS

Stereo Processing by Semiglobal Matching and Mutual Information

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2008
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Deep Discrete Flow

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2015
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

PatchBatch: A Batch Augmented Loss for Optical Flow

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL