Corpus ID: 195347936

Deep Semantic Matching for Optical Flow

@article{Bai2016DeepSM,
  title={Deep Semantic Matching for Optical Flow},
  author={M. Bai and W. Luo and Kaustav Kundu and R. Urtasun},
  journal={ArXiv},
  year={2016},
  volume={abs/1604.01827}
}
  • M. Bai, W. Luo, +1 author R. Urtasun
  • Published 2016
  • Computer Science
  • ArXiv
  • We tackle the problem of estimating optical flow from a monocular camera in the context of autonomous driving. We build on the observation that the scene is typically composed of a static background, as well as a relatively small number of traffic participants which move rigidly in 3D. We propose to estimate the traffic participants using instance-level segmentation. For each traffic participant, we use the epipolar constraints that govern each independent motion for faster and more accurate… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Deep Discrete Flow
    57
    Deep Image Homography Estimation
    125
    Building Deep Networks on Grassmann Manifolds
    45
    cvpaper.challenge in 2016: Futuristic Computer Vision through 1, 600 Papers Survey

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 44 REFERENCES
    Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation
    283
    Robust Monocular Epipolar Flow Estimation
    121
    Monocular 3D Object Detection for Autonomous Driving
    355
    A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
    887
    Optical Flow with Semantic Segmentation and Localized Layers
    126
    Object scene flow for autonomous vehicles
    871
    Instance-Level Segmentation with Deep Densely Connected MRFs
    27
    FlowNet: Learning Optical Flow with Convolutional Networks
    1697
    Are we ready for autonomous driving? The KITTI vision benchmark suite
    4545
    DeepFlow: Large Displacement Optical Flow with Deep Matching
    742