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/MonoViT(MS+1024x320)

MonoViT(MS+1024x320)

Reported on 14 benchmarks across 2 tasks · 1 paper · 8 SOTA

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

Computer Vision7 results

  • Depth EstimationonKITTI Eigen split unsupervised
    Delta < 1.25· 2022-08-06
    0.912
    best: 0.94 (SPIdepth)
    SOTA
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543
  • Depth EstimationonKITTI Eigen split unsupervised
    Delta < 1.25^2· 2022-08-06
    0.969
    best: 0.973 (SPIdepth)
    SOTA
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543
  • Depth EstimationonKITTI Eigen split unsupervised
    Delta < 1.25^3· 2022-08-06
    0.985
    best: 0.986 (Jasmine)
    SOTA
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543
  • Depth EstimationonKITTI Eigen split unsupervised
    RMSE log· 2022-08-06
    0.169
    best: 0.153 (SPIdepth)
    SOTA
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543
  • Depth EstimationonKITTI Eigen split unsupervised
    RMSE· 2022-08-06
    4.202
    best: 3.662 (SPIdepth)
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543
  • Depth EstimationonKITTI Eigen split unsupervised
    Sq Rel· 2022-08-06
    0.671
    best: 0.785 (Dyna-DM)
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543
  • Depth EstimationonKITTI Eigen split unsupervised
    absolute relative error· 2022-08-06
    0.093
    best: 0.071 (SPIdepth)
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543

Methodology7 results

  • 3DonKITTI Eigen split unsupervised
    Delta < 1.25· 2022-08-06
    0.912
    best: 0.94 (SPIdepth)
    SOTA
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543
  • 3DonKITTI Eigen split unsupervised
    Delta < 1.25^2· 2022-08-06
    0.969
    best: 0.973 (SPIdepth)
    SOTA
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543
  • 3DonKITTI Eigen split unsupervised
    Delta < 1.25^3· 2022-08-06
    0.985
    best: 0.986 (Jasmine)
    SOTA
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543
  • 3DonKITTI Eigen split unsupervised
    RMSE log· 2022-08-06
    0.169
    best: 0.153 (SPIdepth)
    SOTA
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543
  • 3DonKITTI Eigen split unsupervised
    RMSE· 2022-08-06
    4.202
    best: 3.662 (SPIdepth)
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543
  • 3DonKITTI Eigen split unsupervised
    Sq Rel· 2022-08-06
    0.671
    best: 0.785 (Dyna-DM)
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543
  • 3DonKITTI Eigen split unsupervised
    absolute relative error· 2022-08-06
    0.093
    best: 0.071 (SPIdepth)
    MonoViT: Self-Supervised Monocular Depth Estimation with a Vision TransformerarXiv:2208.03543