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/JAXNeRF

JAXNeRF

Reported on 6 benchmarks across 1 task · 1 paper · 6 SOTA

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

Computer Vision6 results

  • Novel View SynthesisonNeRF
    LPIPS· 2022-07-30
    0.051
    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 SynthesisonNeRF
    PSNR· 2022-07-30
    31.65
    best: 34.66 (Deformable Beta Splatting)
    SOTA
    MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile ArchitecturesarXiv:2208.00277
  • Novel View SynthesisonNeRF
    SSIM· 2022-07-30
    0.952
    best: 0.973 (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
    0.173
    best: 0.149 (TensoRF + NeRFLiX)
    SOTA
    MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile ArchitecturesarXiv:2208.00277
  • Novel View SynthesisonLLFF
    PSNR· 2022-07-30
    26.92
    best: 27.39 (TensoRF + NeRFLiX)
    SOTA
    MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile ArchitecturesarXiv:2208.00277
  • Novel View SynthesisonLLFF
    SSIM· 2022-07-30
    0.831
    best: 0.867 (TensoRF + NeRFLiX)
    SOTA
    MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile ArchitecturesarXiv:2208.00277