Image-to-Image Translation
Image-to-Image Translation is a task in computer vision and machine learning where the goal is to learn a mapping between an input image and an output image, such that the output image can be used to perform a specific task, such as style transfer, data augmentation, or image restoration.
( Image credit: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks )
Papers
Showing 1–10 of 1184 papers
All datasetsSYNTHIA-to-CityscapesGTAV-to-Cityscapes LabelsCityscapes Labels-to-PhotoADE20K Labels-to-PhotosCOCO-Stuff Labels-to-PhotosADE20K-Outdoor Labels-to-PhotosCelebA-HQCityscapes-to-Foggy Cityscapescat2dogCityscapes Photo-to-LabelsBCIFLIR
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | HRDA + PiPa | mIoU (13 classes) | 74.8 | — | Unverified |
| 2 | MIC | mIoU (13 classes) | 74 | — | Unverified |
| 3 | HRDA | mIoU (13 classes) | 72.4 | — | Unverified |
| 4 | SePiCo | mIoU (13 classes) | 71.4 | — | Unverified |
| 5 | CAMix (w DAFormer) | mIoU (13 classes) | 69.2 | — | Unverified |
| 6 | DAFormer + ProCST | mIoU (13 classes) | 68.2 | — | Unverified |
| 7 | DAFormer | mIoU (13 classes) | 67.4 | — | Unverified |
| 8 | TransDA-B | mIoU (13 classes) | 66.3 | — | Unverified |
| 9 | CPSL | mIoU (13 classes) | 65.3 | — | Unverified |
| 10 | ProDA+CRA | mIoU (13 classes) | 63.7 | — | Unverified |