Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/LINF-LP

LINF-LP

Reported on 16 benchmarks across 4 tasks · 1 paper

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

Computer Vision8 results

Image Super-ResolutiononDIV2K val - 4x upscaling
LPIPS· uses extra data· 2024-03-16
0.105
best: 0.0893 (AESOP)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988
Image Super-ResolutiononDIV2K val - 4x upscaling
LRPSNR· uses extra data· 2024-03-16
47.3
best: 53.3 (FxSR-PD t=0.0)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988
Image Super-ResolutiononDIV2K val - 4x upscaling
PSNR· uses extra data· 2024-03-16
28
best: 29.25 (EDSR)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988
Image Super-ResolutiononDIV2K val - 4x upscaling
SSIM· uses extra data· 2024-03-16
0.78
best: 0.9017 (EDSR)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988
3D Object Super-ResolutiononDIV2K val - 4x upscaling
LPIPS· uses extra data· 2024-03-16
0.105
best: 0.0893 (AESOP)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988
3D Object Super-ResolutiononDIV2K val - 4x upscaling
LRPSNR· uses extra data· 2024-03-16
47.3
best: 53.3 (FxSR-PD t=0.0)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988
3D Object Super-ResolutiononDIV2K val - 4x upscaling
PSNR· uses extra data· 2024-03-16
28
best: 29.25 (EDSR)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988
3D Object Super-ResolutiononDIV2K val - 4x upscaling
SSIM· uses extra data· 2024-03-16
0.78
best: 0.9017 (EDSR)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988

Graphs4 results

Super-ResolutiononDIV2K val - 4x upscaling
LPIPS· uses extra data· 2024-03-16
0.105
best: 0.0893 (AESOP)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988
Super-ResolutiononDIV2K val - 4x upscaling
LRPSNR· uses extra data· 2024-03-16
47.3
best: 53.3 (FxSR-PD t=0.0)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988
Super-ResolutiononDIV2K val - 4x upscaling
PSNR· uses extra data· 2024-03-16
28
best: 29.25 (EDSR)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988
Super-ResolutiononDIV2K val - 4x upscaling
SSIM· uses extra data· 2024-03-16
0.78
best: 0.9017 (EDSR)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988

Methodology4 results

16konDIV2K val - 4x upscaling
LPIPS· uses extra data· 2024-03-16
0.105
best: 0.0893 (AESOP)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988
16konDIV2K val - 4x upscaling
LRPSNR· uses extra data· 2024-03-16
47.3
best: 53.3 (FxSR-PD t=0.0)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988
16konDIV2K val - 4x upscaling
PSNR· uses extra data· 2024-03-16
28
best: 29.25 (EDSR)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988
16konDIV2K val - 4x upscaling
SSIM· uses extra data· 2024-03-16
0.78
best: 0.9017 (EDSR)
Boosting Flow-based Generative Super-Resolution Models via Learned Prior arXiv:2403.10988