A Fusion Approach for Multi-Frame Optical Flow Estimation

@article{Ren2019AFA,
  title={A Fusion Approach for Multi-Frame Optical Flow Estimation},
  author={Zhile Ren and O. Gallo and Deqing Sun and Ming-Hsuan Yang and Erik B. Sudderth and J. Kautz},
  journal={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2019},
  pages={2077-2086}
}
  • Zhile Ren, O. Gallo, +3 authors J. Kautz
  • Published 2019
  • Computer Science
  • 2019 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • To date, top-performing optical flow estimation methods only take pairs of consecutive frames into account. While elegant and appealing, the idea of using more than two frames has not yet produced state-of-the-art results. We present a simple, yet effective fusion approach for multi-frame optical flow that benefits from longer-term temporal cues. Our method first warps the optical flow from previous frames to the current, thereby yielding multiple plausible estimates. It then fuses the… CONTINUE READING
    20 Citations

    Figures, Tables, and Topics from this paper

    A Deep Temporal Fusion Framework for Scene Flow Using a Learnable Motion Model and Occlusions
    • 2
    • PDF
    Improved Discrete Optical Flow Estimation With Triple Image Matching Cost
    • 1
    • 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
    • 45
    • PDF
    KalmanFlow 2.0: Efficient Video Optical Flow Estimation via Context-Aware Kalman Filtering
    • 2
    Optical Flow Estimation in the Deep Learning Age
    • 1
    • PDF
    ScopeFlow: Dynamic Scene Scoping for Optical Flow
    • Aviram Bar-Haim, L. Wolf
    • Computer Science
    • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2020
    • 11
    • PDF
    Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching
    • 2
    • Highly Influenced
    • PDF
    SelFlow: Self-Supervised Learning of Optical Flow
    • 82
    • Highly Influenced
    • PDF
    Data challenges in variational optical flow
    • PDF
    The Five Elements of Flow
    • 2
    • PDF

    References

    SHOWING 1-10 OF 50 REFERENCES
    Optical Flow with Geometric Occlusion Estimation and Fusion of Multiple Frames
    • 69
    • Highly Influential
    • PDF
    Modeling temporal coherence for optical flow
    • 105
    • PDF
    ProFlow: Learning to Predict Optical Flow
    • 23
    • PDF
    Optical Flow Estimation Using a Spatial Pyramid Network
    • 426
    • PDF
    FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
    • 1,364
    • Highly Influential
    • PDF
    Accurate Optical Flow via Direct Cost Volume Processing
    • 122
    • PDF
    Motion Detail Preserving Optical Flow Estimation
    • 496
    • PDF
    Multi-frame optical flow estimation using subspace constraints
    • M. Irani
    • Mathematics, Computer Science
    • Proceedings of the Seventh IEEE International Conference on Computer Vision
    • 1999
    • 164
    • PDF
    A Database and Evaluation Methodology for Optical Flow
    • 2,130
    • PDF
    Layered segmentation and optical flow estimation over time
    • 121
    • PDF