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/pix2pix

pix2pix

Reported on 40 benchmarks across 4 tasks · 3 papers · 31 SOTA

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

Medical18 results

Image GenerationonLLVIP
PSNR· 2021-08-24
10.769
best: 12.191 (pyramidpix2pix)
SOTA
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision arXiv:2108.10831
Image GenerationonLLVIP
SSIM· 2021-08-24
0.1757
best: 0.278 (pyramidpix2pix)
SOTA
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision arXiv:2108.10831
Image GenerationonFLIR
PSNR· 2016-11-21
4.19
best: 23.45 (Pix2Next)
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image GenerationonFLIR
SSIM· 2016-11-21
0.05
best: 0.66 (Pix2Next)
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image GenerationonCityscapes Labels-to-Photo
Class IOU· 2016-11-21
0.18
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image GenerationonCityscapes Labels-to-Photo
Per-class Accuracy· 2016-11-21
25
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image GenerationonCityscapes Labels-to-Photo
Per-pixel Accuracy· 2016-11-21
71
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image GenerationonCityscapes Photo-to-Labels
Class IOU· 2016-11-21
0.32
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image GenerationonFundus Fluorescein Angiogram Photographs & Colour Fundus Images of Diabetic Patients
FID· 2016-11-21
48.6
best: 17.3 (VTGAN)
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image ReconstructiononEdge-to-Handbags
FID· 2016-11-21
96.31
best: 0.069 (PI-REC)
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image ReconstructiononEdge-to-Handbags
LPIPS· 2016-11-21
0.234
best: 0.168 (PI-REC)
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image ReconstructiononEdge-to-Shoes
FID· 2016-11-21
197.492
best: 0.015 (PI-REC)
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image ReconstructiononEdge-to-Shoes
LPIPS· 2016-11-21
0.238
best: 0.085 (PI-REC)
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image GenerationonBCI
Average PSNR· 2022-04-25
19.328
best: 21.16 (pyramidpix2pix)
BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix arXiv:2204.11425
Image GenerationonBCI
SSIM· 2022-04-25
0.44
best: 0.477 (pyramidpix2pix)
BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix arXiv:2204.11425
Image GenerationonLLVIP
PSNR· 2021-08-24
10.769
best: 12.191 (pyramidpix2pix)
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision arXiv:2108.10831
Image GenerationonLLVIP
SSIM· 2021-08-24
0.1757
best: 0.278 (pyramidpix2pix)
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision arXiv:2108.10831
Image GenerationonCityscapes Labels-to-Photo
LPIPS
0

Computer Vision12 results

Image-to-Image TranslationonLLVIP
PSNR· 2021-08-24
10.769
best: 12.191 (pyramidpix2pix)
SOTA
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision arXiv:2108.10831
Image-to-Image TranslationonLLVIP
SSIM· 2021-08-24
0.1757
best: 0.278 (pyramidpix2pix)
SOTA
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision arXiv:2108.10831
Image-to-Image TranslationonFLIR
PSNR· 2016-11-21
4.19
best: 23.45 (Pix2Next)
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image-to-Image TranslationonFLIR
SSIM· 2016-11-21
0.05
best: 0.66 (Pix2Next)
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image-to-Image TranslationonCityscapes Labels-to-Photo
Class IOU· 2016-11-21
0.18
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image-to-Image TranslationonCityscapes Labels-to-Photo
Per-class Accuracy· 2016-11-21
25
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image-to-Image TranslationonCityscapes Labels-to-Photo
Per-pixel Accuracy· 2016-11-21
71
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image-to-Image TranslationonCityscapes Photo-to-Labels
Class IOU· 2016-11-21
0.32
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image-to-Image TranslationonFundus Fluorescein Angiogram Photographs & Colour Fundus Images of Diabetic Patients
FID· 2016-11-21
48.6
best: 17.3 (VTGAN)
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
Image-to-Image TranslationonBCI
Average PSNR· 2022-04-25
19.328
best: 21.16 (pyramidpix2pix)
BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix arXiv:2204.11425
Image-to-Image TranslationonBCI
SSIM· 2022-04-25
0.44
best: 0.477 (pyramidpix2pix)
BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix arXiv:2204.11425
Image-to-Image TranslationonCityscapes Labels-to-Photo
LPIPS
0

Miscellaneous12 results

1 Image, 2*2 StitchingonLLVIP
PSNR· 2021-08-24
10.769
best: 12.191 (pyramidpix2pix)
SOTA
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision arXiv:2108.10831
1 Image, 2*2 StitchingonLLVIP
SSIM· 2021-08-24
0.1757
best: 0.278 (pyramidpix2pix)
SOTA
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision arXiv:2108.10831
1 Image, 2*2 StitchingonFLIR
PSNR· 2016-11-21
4.19
best: 23.45 (Pix2Next)
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
1 Image, 2*2 StitchingonFLIR
SSIM· 2016-11-21
0.05
best: 0.66 (Pix2Next)
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
1 Image, 2*2 StitchingonCityscapes Labels-to-Photo
Class IOU· 2016-11-21
0.18
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
1 Image, 2*2 StitchingonCityscapes Labels-to-Photo
Per-class Accuracy· 2016-11-21
25
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
1 Image, 2*2 StitchingonCityscapes Labels-to-Photo
Per-pixel Accuracy· 2016-11-21
71
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
1 Image, 2*2 StitchingonCityscapes Photo-to-Labels
Class IOU· 2016-11-21
0.32
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
1 Image, 2*2 StitchingonFundus Fluorescein Angiogram Photographs & Colour Fundus Images of Diabetic Patients
FID· 2016-11-21
48.6
best: 17.3 (VTGAN)
SOTA
Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
1 Image, 2*2 StitchingonBCI
Average PSNR· 2022-04-25
19.328
best: 21.16 (pyramidpix2pix)
BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix arXiv:2204.11425
1 Image, 2*2 StitchingonBCI
SSIM· 2022-04-25
0.44
best: 0.477 (pyramidpix2pix)
BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix arXiv:2204.11425
1 Image, 2*2 StitchingonCityscapes Labels-to-Photo
LPIPS
0