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/AnyIR

AnyIR

Reported on 8 benchmarks across 3 tasks · 1 paper

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

Computer Vision5 results

  • Image Restorationon5-Degradations
    Average PSNR· 2024-07-18
    29.65
    best: 31.25 (ABAIR)
    Restore Anything Model via Efficient Degradation AdaptationarXiv:2407.13372
  • Image Restorationon5-Degradations
    SSIM· 2024-07-18
    0.901
    best: 0.921 (ABAIR)
    Restore Anything Model via Efficient Degradation AdaptationarXiv:2407.13372
  • Image Restorationon5-Degradation Blind All-in-One Image Restoration
    Average PSNR· 2024-07-18
    29.65
    best: 31.25 (ABAIR)
    Restore Anything Model via Efficient Degradation AdaptationarXiv:2407.13372
  • Unified Image Restorationon5-Degradations
    Average PSNR· 2024-07-18
    29.65
    best: 31.25 (ABAIR)
    Restore Anything Model via Efficient Degradation AdaptationarXiv:2407.13372
  • Unified Image Restorationon5-Degradations
    SSIM· 2024-07-18
    0.901
    best: 0.921 (ABAIR)
    Restore Anything Model via Efficient Degradation AdaptationarXiv:2407.13372

Audio3 results

  • 10-shot image generationon5-Degradations
    Average PSNR· 2024-07-18
    29.65
    best: 31.25 (ABAIR)
    Restore Anything Model via Efficient Degradation AdaptationarXiv:2407.13372
  • 10-shot image generationon5-Degradations
    SSIM· 2024-07-18
    0.901
    best: 0.921 (ABAIR)
    Restore Anything Model via Efficient Degradation AdaptationarXiv:2407.13372
  • 10-shot image generationon5-Degradation Blind All-in-One Image Restoration
    Average PSNR· 2024-07-18
    29.65
    best: 31.25 (ABAIR)
    Restore Anything Model via Efficient Degradation AdaptationarXiv:2407.13372