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/PULSE

PULSE

Reported on 27 benchmarks across 5 tasks · 4 papers · 6 SOTA

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

Computer Vision17 results

Image Super-ResolutiononCelebA
FID· 2022-12-01
40.33
best: 22.27 (DDNM)
SOTA
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model arXiv:2212.00490
3D Object Super-ResolutiononCelebA
FID· 2022-12-01
40.33
best: 22.27 (DDNM)
SOTA
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model arXiv:2212.00490
Blind Face RestorationonLFW
FID· 2022-06-22
64.86
best: 39.58 (DiffBIR)
SOTA
Towards Robust Blind Face Restoration with Codebook Lookup Transformer arXiv:2206.11253
Blind Face RestorationonWIDER
FID· 2022-06-22
73.59
best: 32.35 (DiffBIR)
SOTA
Towards Robust Blind Face Restoration with Codebook Lookup Transformer arXiv:2206.11253
Blind Face RestorationonCelebA-Test
FID· 2022-12-13
48.33
best: 37.46 (PMRF)
DifFace: Blind Face Restoration with Diffused Error Contraction arXiv:2212.06512
Blind Face RestorationonCelebA-Test
IDS· 2022-12-13
74.97
best: 86.21 (DFDNet)
DifFace: Blind Face Restoration with Diffused Error Contraction arXiv:2212.06512
Blind Face RestorationonCelebA-Test
LPIPS· 2022-12-13
50.8
best: 29.9 (CodeFormer)
DifFace: Blind Face Restoration with Diffused Error Contraction arXiv:2212.06512
Blind Face RestorationonCelebA-Test
PSNR· 2022-12-13
22.14
best: 26.37 (PMRF)
DifFace: Blind Face Restoration with Diffused Error Contraction arXiv:2212.06512
Blind Face RestorationonCelebA-Test
SSIM· 2022-12-13
0.682
best: 0.7073 (PMRF)
DifFace: Blind Face Restoration with Diffused Error Contraction arXiv:2212.06512
Image Super-ResolutiononCelebA
PSNR· 2022-12-01
22.74
best: 31.63 (DDNM)
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model arXiv:2212.00490
Image Super-ResolutiononCelebA
SSIM· 2022-12-01
0.623
best: 0.945 (DDNM)
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model arXiv:2212.00490
3D Object Super-ResolutiononCelebA
PSNR· 2022-12-01
22.74
best: 31.63 (DDNM)
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model arXiv:2212.00490
3D Object Super-ResolutiononCelebA
SSIM· 2022-12-01
0.623
best: 0.945 (DDNM)
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model arXiv:2212.00490
Image Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
PSNR· 2020-03-08
15.74
best: 28.65 (HiFaceGAN)
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models arXiv:2003.03808
Image Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
SSIM· 2020-03-08
0.37
best: 0.816 (HiFaceGAN)
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models arXiv:2003.03808
3D Object Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
PSNR· 2020-03-08
15.74
best: 28.65 (HiFaceGAN)
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models arXiv:2003.03808
3D Object Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
SSIM· 2020-03-08
0.37
best: 0.816 (HiFaceGAN)
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models arXiv:2003.03808

Graphs5 results

Super-ResolutiononCelebA
FID· 2022-12-01
40.33
best: 22.27 (DDNM)
SOTA
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model arXiv:2212.00490
Super-ResolutiononCelebA
PSNR· 2022-12-01
22.74
best: 31.63 (DDNM)
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model arXiv:2212.00490
Super-ResolutiononCelebA
SSIM· 2022-12-01
0.623
best: 0.945 (DDNM)
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model arXiv:2212.00490
Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
PSNR· 2020-03-08
15.74
best: 28.65 (HiFaceGAN)
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models arXiv:2003.03808
Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
SSIM· 2020-03-08
0.37
best: 0.816 (HiFaceGAN)
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models arXiv:2003.03808

Methodology5 results

16konCelebA
FID· 2022-12-01
40.33
best: 1.41 (DDNM)
SOTA
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model arXiv:2212.00490
16konCelebA
PSNR· 2022-12-01
22.74
best: 46.72 (DDNM)
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model arXiv:2212.00490
16konCelebA
SSIM· 2022-12-01
0.623
best: 0.996 (DDNM)
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model arXiv:2212.00490
16konFFHQ 256 x 256 - 4x upscaling
PSNR· 2020-03-08
15.74
best: 28.65 (HiFaceGAN)
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models arXiv:2003.03808
16konFFHQ 256 x 256 - 4x upscaling
SSIM· 2020-03-08
0.37
best: 0.816 (HiFaceGAN)
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models arXiv:2003.03808