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/Resfusion

Resfusion

Reported on 8 benchmarks across 5 tasks · 1 paper · 1 SOTA

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

Computer Vision7 results

Rain RemovalonRaindrop
SSIM· 2023-11-25
0.938
SOTA
Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise arXiv:2311.14900
Image EnhancementonLOL
Average PSNR· 2023-11-25
24.63
best: 29.185 (CFWD)
Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise arXiv:2311.14900
Image EnhancementonLOL
LPIPS· 2023-11-25
0.107
best: 0.069 (BEM_)
Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise arXiv:2311.14900
Image EnhancementonLOL
SSIM· 2023-11-25
0.86
best: 0.93 (PyDiff)
Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise arXiv:2311.14900
Rain RemovalonRaindrop
PSNR· 2023-11-25
32.61
best: 34.55 (TransWeather)
Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise arXiv:2311.14900
Image EditingonISTD
MAE· 2023-11-25
4.81
best: 4.79 (ShadowFormer)
Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise arXiv:2311.14900
Shadow RemovalonISTD
MAE· 2023-11-25
4.81
best: 4.79 (ShadowFormer)
Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise arXiv:2311.14900

Methodology1 result

16konISTD
MAE· 2023-11-25
4.81
best: 4.79 (ShadowFormer)
Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise arXiv:2311.14900