PIRM (Perceptual Image Restoration and Manipulation)
Introduced by Blau et al. in The 2018 PIRM Challenge on Perceptual Image Super-resolution
The PIRM dataset consists of 200 images, which are divided into two equal sets for validation and testing. These images cover diverse contents, including people, objects, environments, flora, natural scenery, etc. Images vary in size, and are typically ~300K pixels in resolution.
Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
PIRM-test
|
RankSRGAN
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
