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/SRGAN

SRGAN

Reported on 112 benchmarks across 4 tasks · 1 paper · 56 SOTA

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

Computer Vision56 results

Image Super-ResolutiononWebFace - 8x upscaling
PSNR· 2016-09-15
24.49
best: 27.21 (GFRNet)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononSet5 - 4x upscaling
MOS· 2016-09-15
3.58
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononSet14 - 4x upscaling
MOS· 2016-09-15
3.72
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
FED· 2016-09-15
0.1097
best: 0.1416 (Super-FAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
FID· 2016-09-15
4.396
best: 1.898 (HiFaceGAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
LLE· 2016-09-15
2.269
best: 2.702 (WaveletCNN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
LPIPS· 2016-09-15
0.1313
best: 0.0723 (HiFaceGAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
MS-SSIM· 2016-09-15
0.935
best: 0.976 (UNET++)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
NIQE· 2016-09-15
7.378
best: 13.901 (SRFBN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
PSNR· 2016-09-15
27.494
best: 30.824 (HiFaceGAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
SSIM· 2016-09-15
0.735
best: 0.859 (UNET++)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononVggFace2 - 8x upscaling
PSNR· 2016-09-15
23.01
best: 25.57 (Full-GWAInet)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononPIRM-test
NIQE· 2016-09-15
2.71
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononBSD100 - 4x upscaling
MOS· 2016-09-15
3.56
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononWebFace - 8x upscaling
PSNR· 2016-09-15
24.49
best: 27.21 (GFRNet)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononSet5 - 4x upscaling
MOS· 2016-09-15
3.58
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononSet14 - 4x upscaling
MOS· 2016-09-15
3.72
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
FED· 2016-09-15
0.1097
best: 0.1416 (Super-FAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
FID· 2016-09-15
4.396
best: 1.898 (HiFaceGAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
LLE· 2016-09-15
2.269
best: 2.702 (WaveletCNN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
LPIPS· 2016-09-15
0.1313
best: 0.0723 (HiFaceGAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
MS-SSIM· 2016-09-15
0.935
best: 0.976 (UNET++)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
NIQE· 2016-09-15
7.378
best: 13.901 (SRFBN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
PSNR· 2016-09-15
27.494
best: 30.824 (HiFaceGAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
SSIM· 2016-09-15
0.735
best: 0.859 (UNET++)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononVggFace2 - 8x upscaling
PSNR· 2016-09-15
23.01
best: 25.57 (Full-GWAInet)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononPIRM-test
NIQE· 2016-09-15
2.71
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononBSD100 - 4x upscaling
MOS· 2016-09-15
3.56
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononSet5 - 4x upscaling
PSNR· 2016-09-15
29.4
best: 33.38 (HMA†)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononSet5 - 4x upscaling
SSIM· 2016-09-15
0.8472
best: 0.9103 (Hi-IR-L)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononSet14 - 4x upscaling
PSNR· 2016-09-15
25.99
best: 29.54 (DRCT-L)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononSet14 - 4x upscaling
SSIM· 2016-09-15
0.7397
best: 0.894 (Edge-informed SR)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
FID· 2016-09-15
156.07
best: 5.36 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
MS-SSIM· 2016-09-15
0.757
best: 0.971 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
PSNR· 2016-09-15
17.57
best: 28.65 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
SSIM· 2016-09-15
0.415
best: 0.816 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 1024 x 1024 - 4x upscaling
FID· 2016-09-15
60.67
best: 1.978 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 1024 x 1024 - 4x upscaling
MS-SSIM· 2016-09-15
0.807
best: 0.975 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 1024 x 1024 - 4x upscaling
PSNR· 2016-09-15
21.49
best: 34.1 (CAGFace)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononFFHQ 1024 x 1024 - 4x upscaling
SSIM· 2016-09-15
0.515
best: 0.906 (CAGFace)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononBSD100 - 4x upscaling
PSNR· 2016-09-15
25.16
best: 28.16 (DRCT-L)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Image Super-ResolutiononBSD100 - 4x upscaling
SSIM· 2016-09-15
0.6688
best: 0.851 (Edge-informed SR)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononSet5 - 4x upscaling
PSNR· 2016-09-15
29.4
best: 33.38 (HMA†)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononSet5 - 4x upscaling
SSIM· 2016-09-15
0.8472
best: 0.9103 (Hi-IR-L)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononSet14 - 4x upscaling
PSNR· 2016-09-15
25.99
best: 29.54 (DRCT-L)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononSet14 - 4x upscaling
SSIM· 2016-09-15
0.7397
best: 0.894 (Edge-informed SR)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
FID· 2016-09-15
156.07
best: 5.36 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
MS-SSIM· 2016-09-15
0.757
best: 0.971 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
PSNR· 2016-09-15
17.57
best: 28.65 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
SSIM· 2016-09-15
0.415
best: 0.816 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 1024 x 1024 - 4x upscaling
FID· 2016-09-15
60.67
best: 1.978 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 1024 x 1024 - 4x upscaling
MS-SSIM· 2016-09-15
0.807
best: 0.975 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 1024 x 1024 - 4x upscaling
PSNR· 2016-09-15
21.49
best: 34.1 (CAGFace)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononFFHQ 1024 x 1024 - 4x upscaling
SSIM· 2016-09-15
0.515
best: 0.906 (CAGFace)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononBSD100 - 4x upscaling
PSNR· 2016-09-15
25.16
best: 28.16 (DRCT-L)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
3D Object Super-ResolutiononBSD100 - 4x upscaling
SSIM· 2016-09-15
0.6688
best: 0.851 (Edge-informed SR)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802

Graphs28 results

Super-ResolutiononWebFace - 8x upscaling
PSNR· 2016-09-15
24.49
best: 27.21 (GFRNet)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononSet5 - 4x upscaling
MOS· 2016-09-15
3.58
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononSet14 - 4x upscaling
MOS· 2016-09-15
3.72
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
FED· 2016-09-15
0.1097
best: 0.1416 (Super-FAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
FID· 2016-09-15
4.396
best: 1.898 (HiFaceGAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
LLE· 2016-09-15
2.269
best: 2.702 (WaveletCNN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
LPIPS· 2016-09-15
0.1313
best: 0.0723 (HiFaceGAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
MS-SSIM· 2016-09-15
0.935
best: 0.976 (UNET++)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
NIQE· 2016-09-15
7.378
best: 13.901 (SRFBN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
PSNR· 2016-09-15
27.494
best: 30.824 (HiFaceGAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 512 x 512 - 4x upscaling
SSIM· 2016-09-15
0.735
best: 0.859 (UNET++)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononVggFace2 - 8x upscaling
PSNR· 2016-09-15
23.01
best: 25.57 (Full-GWAInet)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononPIRM-test
NIQE· 2016-09-15
2.71
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononBSD100 - 4x upscaling
MOS· 2016-09-15
3.56
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononSet5 - 4x upscaling
PSNR· 2016-09-15
29.4
best: 33.38 (HMA†)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononSet5 - 4x upscaling
SSIM· 2016-09-15
0.8472
best: 0.9103 (Hi-IR-L)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononSet14 - 4x upscaling
PSNR· 2016-09-15
25.99
best: 29.54 (DRCT-L)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononSet14 - 4x upscaling
SSIM· 2016-09-15
0.7397
best: 0.894 (Edge-informed SR)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
FID· 2016-09-15
156.07
best: 5.36 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
MS-SSIM· 2016-09-15
0.757
best: 0.971 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
PSNR· 2016-09-15
17.57
best: 28.65 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 256 x 256 - 4x upscaling
SSIM· 2016-09-15
0.415
best: 0.816 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 1024 x 1024 - 4x upscaling
FID· 2016-09-15
60.67
best: 1.978 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 1024 x 1024 - 4x upscaling
MS-SSIM· 2016-09-15
0.807
best: 0.975 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 1024 x 1024 - 4x upscaling
PSNR· 2016-09-15
21.49
best: 34.1 (CAGFace)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononFFHQ 1024 x 1024 - 4x upscaling
SSIM· 2016-09-15
0.515
best: 0.906 (CAGFace)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononBSD100 - 4x upscaling
PSNR· 2016-09-15
25.16
best: 28.16 (DRCT-L)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
Super-ResolutiononBSD100 - 4x upscaling
SSIM· 2016-09-15
0.6688
best: 0.851 (Edge-informed SR)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802

Methodology28 results

16konWebFace - 8x upscaling
PSNR· 2016-09-15
24.49
best: 27.21 (GFRNet)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konSet5 - 4x upscaling
MOS· 2016-09-15
3.58
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konSet14 - 4x upscaling
MOS· 2016-09-15
3.72
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 512 x 512 - 4x upscaling
FED· 2016-09-15
0.1097
best: 0.1416 (Super-FAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 512 x 512 - 4x upscaling
FID· 2016-09-15
4.396
best: 1.898 (HiFaceGAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 512 x 512 - 4x upscaling
LLE· 2016-09-15
2.269
best: 2.702 (WaveletCNN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 512 x 512 - 4x upscaling
LPIPS· 2016-09-15
0.1313
best: 0.0723 (HiFaceGAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 512 x 512 - 4x upscaling
MS-SSIM· 2016-09-15
0.935
best: 0.976 (UNET++)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 512 x 512 - 4x upscaling
NIQE· 2016-09-15
7.378
best: 13.901 (SRFBN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 512 x 512 - 4x upscaling
PSNR· 2016-09-15
27.494
best: 30.824 (HiFaceGAN)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 512 x 512 - 4x upscaling
SSIM· 2016-09-15
0.735
best: 0.859 (UNET++)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konVggFace2 - 8x upscaling
PSNR· 2016-09-15
23.01
best: 25.57 (Full-GWAInet)
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konPIRM-test
NIQE· 2016-09-15
2.71
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konBSD100 - 4x upscaling
MOS· 2016-09-15
3.56
SOTA
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konSet5 - 4x upscaling
PSNR· 2016-09-15
29.4
best: 33.38 (HMA†)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konSet5 - 4x upscaling
SSIM· 2016-09-15
0.8472
best: 0.9103 (Hi-IR-L)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konSet14 - 4x upscaling
PSNR· 2016-09-15
25.99
best: 29.54 (DRCT-L)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konSet14 - 4x upscaling
SSIM· 2016-09-15
0.7397
best: 0.894 (Edge-informed SR)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 256 x 256 - 4x upscaling
FID· 2016-09-15
156.07
best: 5.36 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 256 x 256 - 4x upscaling
MS-SSIM· 2016-09-15
0.757
best: 0.971 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 256 x 256 - 4x upscaling
PSNR· 2016-09-15
17.57
best: 28.65 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 256 x 256 - 4x upscaling
SSIM· 2016-09-15
0.415
best: 0.816 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 1024 x 1024 - 4x upscaling
FID· 2016-09-15
60.67
best: 1.978 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 1024 x 1024 - 4x upscaling
MS-SSIM· 2016-09-15
0.807
best: 0.975 (HiFaceGAN)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 1024 x 1024 - 4x upscaling
PSNR· 2016-09-15
21.49
best: 34.1 (CAGFace)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konFFHQ 1024 x 1024 - 4x upscaling
SSIM· 2016-09-15
0.515
best: 0.906 (CAGFace)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konBSD100 - 4x upscaling
PSNR· 2016-09-15
25.16
best: 28.16 (DRCT-L)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
16konBSD100 - 4x upscaling
SSIM· 2016-09-15
0.6688
best: 0.851 (Edge-informed SR)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802