TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/PWC-Net

PWC-Net

Reported on 7 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision7 results

  • Optical Flow EstimationonKITTI 2015 (train)
    EPE· 2017-09-07
    10.35
    best: 13.17 (HD3)
    SOTA
    PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost VolumearXiv:1709.02371
  • Optical Flow EstimationonKITTI 2015 (train)
    F1-all· 2017-09-07
    33.7
    SOTA
    PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost VolumearXiv:1709.02371
  • Dense Pixel Correspondence EstimationonHPatches
    Viewpoint I AEPE· 2017-09-07
    4.43
    best: 36.94 (SPyNet)
    PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost VolumearXiv:1709.02371
  • Dense Pixel Correspondence EstimationonHPatches
    Viewpoint II AEPE· 2017-09-07
    11.44
    best: 50.92 (SPyNet)
    PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost VolumearXiv:1709.02371
  • Dense Pixel Correspondence EstimationonHPatches
    Viewpoint III AEPE· 2017-09-07
    15.47
    best: 54.29 (SPyNet)
    PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost VolumearXiv:1709.02371
  • Dense Pixel Correspondence EstimationonHPatches
    Viewpoint IV AEPE· 2017-09-07
    20.17
    best: 62.6 (SPyNet)
    PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost VolumearXiv:1709.02371
  • Dense Pixel Correspondence EstimationonHPatches
    Viewpoint V AEPE· 2017-09-07
    28.3
    best: 72.57 (SPyNet)
    PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost VolumearXiv:1709.02371