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/3DDFA_V2

3DDFA_V2

Reported on 35 benchmarks across 5 tasks · 1 paper · 10 SOTA

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

Computer Vision14 results

  • Face ReconstructiononFlorence
    Mean NME· 2020-09-21
    3.56
    SOTA
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • Face ReconstructiononStirling-HQ (FG2018 3D face reconstruction challenge)
    Mean Reconstruction Error (mm)· 2020-09-21
    1.91
    best: 1.89 (DECA)
    SOTA
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3D Face ReconstructiononFlorence
    Mean NME· 2020-09-21
    3.56
    SOTA
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3D Face ReconstructiononStirling-HQ (FG2018 3D face reconstruction challenge)
    Mean Reconstruction Error (mm)· 2020-09-21
    1.91
    best: 1.89 (DECA)
    SOTA
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • Face ReconstructiononStirling-LQ (FG2018 3D face reconstruction challenge)
    Mean Reconstruction Error (mm)· 2020-09-21
    2.1
    best: 1.91 (DECA)
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • Face ReconstructiononNoW Benchmark
    Mean Reconstruction Error (mm)· 2020-09-21
    1.57
    best: 1.01 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • Face ReconstructiononNoW Benchmark
    Median Reconstruction Error· 2020-09-21
    1.23
    best: 0.81 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • Face ReconstructiononNoW Benchmark
    Stdev Reconstruction Error (mm)· 2020-09-21
    1.39
    best: 0.84 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • Face ReconstructiononAFLW
    Mean NME· 2020-09-21
    4.43
    best: 4.55 (3DDFA)
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3D Face ReconstructiononStirling-LQ (FG2018 3D face reconstruction challenge)
    Mean Reconstruction Error (mm)· 2020-09-21
    2.1
    best: 1.91 (DECA)
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3D Face ReconstructiononNoW Benchmark
    Mean Reconstruction Error (mm)· 2020-09-21
    1.57
    best: 1.01 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3D Face ReconstructiononNoW Benchmark
    Median Reconstruction Error· 2020-09-21
    1.23
    best: 0.81 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3D Face ReconstructiononNoW Benchmark
    Stdev Reconstruction Error (mm)· 2020-09-21
    1.39
    best: 0.84 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3D Face ReconstructiononAFLW
    Mean NME· 2020-09-21
    4.43
    best: 4.55 (3DDFA)
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960

Music7 results

  • Facial Recognition and ModellingonFlorence
    Mean NME· 2020-09-21
    3.56
    SOTA
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • Facial Recognition and ModellingonStirling-HQ (FG2018 3D face reconstruction challenge)
    Mean Reconstruction Error (mm)· 2020-09-21
    1.91
    best: 1.89 (DECA)
    SOTA
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • Facial Recognition and ModellingonAFLW
    Mean NME· 2020-09-21
    4.43
    best: 4.55 (3DDFA)
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • Facial Recognition and ModellingonStirling-LQ (FG2018 3D face reconstruction challenge)
    Mean Reconstruction Error (mm)· 2020-09-21
    2.1
    best: 1.91 (DECA)
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • Facial Recognition and ModellingonNoW Benchmark
    Mean Reconstruction Error (mm)· 2020-09-21
    1.57
    best: 1.01 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • Facial Recognition and ModellingonNoW Benchmark
    Median Reconstruction Error· 2020-09-21
    1.23
    best: 0.81 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • Facial Recognition and ModellingonNoW Benchmark
    Stdev Reconstruction Error (mm)· 2020-09-21
    1.39
    best: 0.84 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960

Methodology7 results

  • 3DonFlorence
    Mean NME· 2020-09-21
    3.56
    SOTA
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3DonStirling-HQ (FG2018 3D face reconstruction challenge)
    Mean Reconstruction Error (mm)· 2020-09-21
    1.91
    best: 1.89 (DECA)
    SOTA
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3DonStirling-LQ (FG2018 3D face reconstruction challenge)
    Mean Reconstruction Error (mm)· 2020-09-21
    2.1
    best: 1.91 (DECA)
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3DonNoW Benchmark
    Mean Reconstruction Error (mm)· 2020-09-21
    1.57
    best: 1.01 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3DonNoW Benchmark
    Median Reconstruction Error· 2020-09-21
    1.23
    best: 0.81 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3DonNoW Benchmark
    Stdev Reconstruction Error (mm)· 2020-09-21
    1.39
    best: 0.84 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3DonAFLW
    Mean NME· 2020-09-21
    4.43
    best: 4.55 (3DDFA)
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960

Medical7 results

  • 3D Face ModellingonFlorence
    Mean NME· 2020-09-21
    3.56
    SOTA
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3D Face ModellingonStirling-HQ (FG2018 3D face reconstruction challenge)
    Mean Reconstruction Error (mm)· 2020-09-21
    1.91
    best: 1.89 (DECA)
    SOTA
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3D Face ModellingonAFLW
    Mean NME· 2020-09-21
    4.43
    best: 4.55 (3DDFA)
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3D Face ModellingonStirling-LQ (FG2018 3D face reconstruction challenge)
    Mean Reconstruction Error (mm)· 2020-09-21
    2.1
    best: 1.91 (DECA)
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3D Face ModellingonNoW Benchmark
    Mean Reconstruction Error (mm)· 2020-09-21
    1.57
    best: 1.01 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3D Face ModellingonNoW Benchmark
    Median Reconstruction Error· 2020-09-21
    1.23
    best: 0.81 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960
  • 3D Face ModellingonNoW Benchmark
    Stdev Reconstruction Error (mm)· 2020-09-21
    1.39
    best: 0.84 (DenseLandmarks (Multi-view))
    Towards Fast, Accurate and Stable 3D Dense Face AlignmentarXiv:2009.09960