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/PersistentNature

PersistentNature

Reported on 8 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 Vision4 results

  • Scene GenerationonGoogleEarth
    FID· 2023-03-23
    123.83
    best: 86.94 (GaussianCity)
    SOTA
    Persistent Nature: A Generative Model of Unbounded 3D WorldsarXiv:2303.13515
  • Scene GenerationonGoogleEarth
    Camera Error· 2023-03-23
    86.371
    best: 0.057 (GaussianCity)
    Persistent Nature: A Generative Model of Unbounded 3D WorldsarXiv:2303.13515
  • Scene GenerationonGoogleEarth
    Depth Error· 2023-03-23
    0.326
    best: 0.136 (GaussianCity)
    Persistent Nature: A Generative Model of Unbounded 3D WorldsarXiv:2303.13515
  • Scene GenerationonGoogleEarth
    KID· 2023-03-23
    0.109
    best: 0.358 (SGAM)
    Persistent Nature: A Generative Model of Unbounded 3D WorldsarXiv:2303.13515

Methodology4 results

  • 16konGoogleEarth
    FID· 2023-03-23
    123.83
    best: 86.94 (GaussianCity)
    SOTA
    Persistent Nature: A Generative Model of Unbounded 3D WorldsarXiv:2303.13515
  • 16konGoogleEarth
    Camera Error· 2023-03-23
    86.371
    best: 0.057 (GaussianCity)
    Persistent Nature: A Generative Model of Unbounded 3D WorldsarXiv:2303.13515
  • 16konGoogleEarth
    Depth Error· 2023-03-23
    0.326
    best: 0.136 (GaussianCity)
    Persistent Nature: A Generative Model of Unbounded 3D WorldsarXiv:2303.13515
  • 16konGoogleEarth
    KID· 2023-03-23
    0.109
    best: 0.358 (SGAM)
    Persistent Nature: A Generative Model of Unbounded 3D WorldsarXiv:2303.13515