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

@article{Chen2016FullFO,
  title={Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids},
  author={Qifeng Chen and V. Koltun},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={4706-4714}
}
  • Qifeng Chen, V. Koltun
  • Published 2016
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
We present a global optimization approach to optical flow estimation. The approach optimizes a classical optical flow objective over the full space of mappings between discrete grids. No descriptor matching is used. The highly regular structure of the space of mappings enables optimizations that reduce the computational complexity of the algorithm's inner loop from quadratic to linear and support efficient matching of tens of thousands of nodes to tens of thousands of displacements. We show… Expand
129 Citations
SceneFlowFields: Dense Interpolation of Sparse Scene Flow Correspondences
  • 24
  • PDF
Accurate Optical Flow via Direct Cost Volume Processing
  • 136
  • PDF
Fast Optical Flow Using Dense Inverse Search
  • 182
  • PDF
Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation
  • Junhwa Hur, S. Roth
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
  • 74
  • PDF
Order-Adaptive and Illumination-Aware Variational Optical Flow Refinement
  • 14
  • Highly Influenced
  • PDF
ProbFlow: Joint Optical Flow and Uncertainty Estimation
  • 25
  • PDF
Efficient Segmentation-Based PatchMatch for Large Displacement Optical Flow Estimation
  • 3
Hierarchical Discrete Distribution Decomposition for Match Density Estimation
  • 88
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 49 REFERENCES
Discrete Optimization for Optical Flow
  • 102
  • Highly Influential
  • PDF
EpicFlow: Edge-preserving interpolation of correspondences for optical flow
  • 623
  • Highly Influential
  • PDF
TriangleFlow: Optical Flow with Triangulation-Based Higher-Order Likelihoods
  • 46
  • PDF
Dense, accurate optical flow estimation with piecewise parametric model
  • J. Yang, Hongdong Li
  • Mathematics, Computer Science
  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
  • 102
  • PDF
Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation
  • T. Brox, Jitendra Malik
  • Mathematics, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2011
  • 1,228
  • PDF
Motion Detail Preserving Optical Flow Estimation
  • 507
  • PDF
DeepFlow: Large Displacement Optical Flow with Deep Matching
  • 819
  • PDF
A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them
  • 461
  • Highly Influential
  • PDF
Large displacement optical flow computation withoutwarping
  • 140
  • PDF
...
1
2
3
4
5
...