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/Manydepth2

Manydepth2

Reported on 24 benchmarks across 3 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 Vision13 results

  • Depth EstimationonCityscapes
    Absolute relative error (AbsRel)· 2023-12-23
    0.097
    best: 0.089 (SwinMTL)
    SOTA
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • Depth EstimationonCityscapes
    RMSE· 2023-12-23
    5.827
    best: 5.481 (SwinMTL)
    SOTA
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • Depth EstimationonCityscapes
    RMSE log· 2023-12-23
    0.154
    best: 0.139 (SwinMTL)
    SOTA
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • Depth EstimationonCityscapes
    Square relative error (SqRel)· 2023-12-23
    0.792
    SOTA
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • Camera Pose EstimationonKITTI Odometry Benchmark
    Average Rotational Error er[%]· 2023-12-23
    2.205
    SOTA
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • Camera Pose EstimationonKITTI Odometry Benchmark
    Average Translational Error et[%]· 2023-12-23
    7.15
    SOTA
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • Depth EstimationonKITTI Eigen split
    Delta < 1.25· 2023-12-23
    0.909
    best: 0.99 (SPIDepth)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • Depth EstimationonKITTI Eigen split
    Delta < 1.25^2· 2023-12-23
    0.968
    best: 0.999 (SPIDepth)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • Depth EstimationonKITTI Eigen split
    Delta < 1.25^3· 2023-12-23
    0.984
    best: 1 (SPIDepth)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • Depth EstimationonKITTI Eigen split
    RMSE· 2023-12-23
    4.232
    best: 1.394 (SPIDepth)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • Depth EstimationonKITTI Eigen split
    RMSE log· 2023-12-23
    0.649
    best: 0.048 (SPIDepth)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • Depth EstimationonKITTI Eigen split
    Sq Rel· 2023-12-23
    0.17
    best: 0.224 (SfM-Revisited)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • Depth EstimationonKITTI Eigen split
    absolute relative error· 2023-12-23
    0.091
    best: 0.029 (SPIDepth)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268

Methodology11 results

  • 3DonCityscapes
    Absolute relative error (AbsRel)· 2023-12-23
    0.097
    best: 0.089 (SwinMTL)
    SOTA
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • 3DonCityscapes
    RMSE· 2023-12-23
    5.827
    best: 5.481 (SwinMTL)
    SOTA
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • 3DonCityscapes
    RMSE log· 2023-12-23
    0.154
    best: 0.139 (SwinMTL)
    SOTA
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • 3DonCityscapes
    Square relative error (SqRel)· 2023-12-23
    0.792
    SOTA
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • 3DonKITTI Eigen split
    Delta < 1.25· 2023-12-23
    0.909
    best: 0.99 (SPIDepth)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • 3DonKITTI Eigen split
    Delta < 1.25^2· 2023-12-23
    0.968
    best: 0.999 (SPIDepth)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • 3DonKITTI Eigen split
    Delta < 1.25^3· 2023-12-23
    0.984
    best: 1 (SPIDepth)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • 3DonKITTI Eigen split
    RMSE· 2023-12-23
    4.232
    best: 1.394 (SPIDepth)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • 3DonKITTI Eigen split
    RMSE log· 2023-12-23
    0.649
    best: 0.048 (SPIDepth)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • 3DonKITTI Eigen split
    Sq Rel· 2023-12-23
    0.17
    best: 0.224 (SfM-Revisited)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268
  • 3DonKITTI Eigen split
    absolute relative error· 2023-12-23
    0.091
    best: 0.029 (SPIDepth)
    Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesarXiv:2312.15268