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/NeRF

NeRF

Reported on 14 benchmarks across 2 tasks · 3 papers · 7 SOTA

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

Computer Vision12 results

  • Novel View SynthesisonMip-NeRF 360
    LPIPS· 2022-07-30
    0.515
    best: 0.171 (MVGS)
    SOTA
    MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile ArchitecturesarXiv:2208.00277
  • Novel View SynthesisonNeRF
    LPIPS· 2022-07-30
    0.081
    best: 0.028 (Deformable Beta Splatting)
    SOTA
    MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile ArchitecturesarXiv:2208.00277
  • Novel View SynthesisonLLFF
    LPIPS· 2022-07-30
    0.25
    best: 0.149 (TensoRF + NeRFLiX)
    SOTA
    MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile ArchitecturesarXiv:2208.00277
  • Novel View SynthesisonX3D
    PSNR· 2020-03-19
    32.49
    best: 51.37 (SAX-NeRF)
    SOTA
    NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisarXiv:2003.08934
  • Novel View SynthesisonX3D
    SSIM· 2020-03-19
    0.977
    best: 0.9994 (SAX-NeRF)
    SOTA
    NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisarXiv:2003.08934
  • Novel View SynthesisonDONeRF: Evaluation Dataset
    PSNR· 2023-01-05
    30.9
    best: 35.1 (HyperReel)
    HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned SamplingarXiv:2301.02238
  • Novel View SynthesisonMip-NeRF 360
    PSNR· 2022-07-30
    21.46
    best: Infinity (Li Auto Inc.)
    MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile ArchitecturesarXiv:2208.00277
  • Novel View SynthesisonMip-NeRF 360
    SSIM· 2022-07-30
    0.458
    best: Infinity (Li Auto Inc.)
    MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile ArchitecturesarXiv:2208.00277
  • Novel View SynthesisonNeRF
    PSNR· 2022-07-30
    31
    best: 34.66 (Deformable Beta Splatting)
    MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile ArchitecturesarXiv:2208.00277
  • Novel View SynthesisonNeRF
    SSIM· 2022-07-30
    0.947
    best: 0.973 (Deformable Beta Splatting)
    MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile ArchitecturesarXiv:2208.00277
  • Novel View SynthesisonLLFF
    PSNR· 2022-07-30
    26.5
    best: 27.39 (TensoRF + NeRFLiX)
    MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile ArchitecturesarXiv:2208.00277
  • Novel View SynthesisonLLFF
    SSIM· 2022-07-30
    0.811
    best: 0.867 (TensoRF + NeRFLiX)
    MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile ArchitecturesarXiv:2208.00277

Medical2 results

  • X-RayonX3D
    PSNR· 2020-03-19
    32.15
    best: 37.25 (SAX-NeRF)
    SOTA
    NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisarXiv:2003.08934
  • X-RayonX3D
    SSIM· 2020-03-19
    0.9354
    best: 0.9753 (SAX-NeRF)
    SOTA
    NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisarXiv:2003.08934