# Arbitrary-scale Super-resolution on Urban100 (PSNR-Y)

Source: [Arbitrary-scale Super-resolution on Urban100 (PSNR-Y)](<https://www.sota2.com/research/sota/arbitrary-scale-super-resolution-on-urban100-psnr-y>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-19T07:23:09.921Z

Evaluation of Arbitrary-scale Super-resolution performance on the Urban100 dataset, measured using PSNR on the luminance channel (PSNR-Y).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Arbitrary-scale Super-resolution |
| Dataset (including any stated split) | Urban100 |
| Metric | PSNR-Y |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [PSNR-Y](<https://www.sota2.com/research/sota/arbitrary-scale-super-resolution-on-urban100-psnr-y.md?metric=PSNR-Y>): Higher is better; unit: SCALAR.

## Recorded results

| Method | PSNR-Y | Result date | Report paper |
| --- | --- | --- | --- |
| LTE-SwinIR | 24.679 | Not recorded | 6a34ccee206542251d7c5e01 |
| LTE-RDN | 24.194 | Not recorded | 6a34ccee206542251d7c5e01 |
| LIIF-RDN | 24.186 | Not recorded | 6a34ccee206542251d7c5e01 |
| GB-LSR-Scalar-ASR | 24.024 | Not recorded | 6a34ccee206542251d7c5e01 |
| LTE-SwinIR | 23.231 | Not recorded | 6a34ccee206542251d7c5e01 |
| LTE-RDN | 22.801 | Not recorded | 6a34ccee206542251d7c5e01 |
| LIIF-RDN | 22.786 | Not recorded | 6a34ccee206542251d7c5e01 |
| GB-LSR-Scalar-ASR | 22.686 | Not recorded | 6a34ccee206542251d7c5e01 |

### LTE-SwinIR

PSNR-Y: 24.679. Result ID: 6a34eca8fbc373592c31c947.

[Reporting paper](<https://www.sota2.com/research/paper/6a34ccee206542251d7c5e01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32528.md>)

[Implementation](<https://github.com/jaewon-lee-b/lte>)

Recorded evaluation configuration: {"Scale":"×6","Trainable parameters":"12.53M"}. This record does not assert independent reproduction.

### LTE-RDN

PSNR-Y: 24.194. Result ID: 6a34eca8fbc373592c31c945.

[Reporting paper](<https://www.sota2.com/research/paper/6a34ccee206542251d7c5e01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32528.md>)

[Implementation](<https://github.com/jaewon-lee-b/lte>)

Recorded evaluation configuration: {"Scale":"×6","Trainable parameters":"22.47M"}. This record does not assert independent reproduction.

### LIIF-RDN

PSNR-Y: 24.186. Result ID: 6a34eca8fbc373592c31c943.

[Reporting paper](<https://www.sota2.com/research/paper/6a34ccee206542251d7c5e01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b11e209131cea23746.md>)

[Implementation](<https://yinboc.github.io/liif/>)

Recorded evaluation configuration: {"Scale":"×6","Trainable parameters":"22.32M"}. This record does not assert independent reproduction.

### GB-LSR-Scalar-ASR

PSNR-Y: 24.024. Result ID: 6a34eca8fbc373592c31c949.

[Reporting paper](<https://www.sota2.com/research/paper/6a34ccee206542251d7c5e01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34ccee206542251d7c5e01.md>)

Recorded evaluation configuration: {"Scale":"×6","Trainable parameters":"22.02M"}. This record does not assert independent reproduction.

### LTE-SwinIR

PSNR-Y: 23.231. Result ID: 6a34eca8fbc373592c31c948.

[Reporting paper](<https://www.sota2.com/research/paper/6a34ccee206542251d7c5e01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32528.md>)

[Implementation](<https://github.com/jaewon-lee-b/lte>)

Recorded evaluation configuration: {"Scale":"×8","Trainable parameters":"12.53M"}. This record does not assert independent reproduction.

### LTE-RDN

PSNR-Y: 22.801. Result ID: 6a34eca8fbc373592c31c946.

[Reporting paper](<https://www.sota2.com/research/paper/6a34ccee206542251d7c5e01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32528.md>)

[Implementation](<https://github.com/jaewon-lee-b/lte>)

Recorded evaluation configuration: {"Scale":"×8","Trainable parameters":"22.47M"}. This record does not assert independent reproduction.

### LIIF-RDN

PSNR-Y: 22.786. Result ID: 6a34eca8fbc373592c31c944.

[Reporting paper](<https://www.sota2.com/research/paper/6a34ccee206542251d7c5e01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b11e209131cea23746.md>)

[Implementation](<https://yinboc.github.io/liif/>)

Recorded evaluation configuration: {"Scale":"×8","Trainable parameters":"22.32M"}. This record does not assert independent reproduction.

### GB-LSR-Scalar-ASR

PSNR-Y: 22.686. Result ID: 6a34eca8fbc373592c31c94a.

[Reporting paper](<https://www.sota2.com/research/paper/6a34ccee206542251d7c5e01.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a34ccee206542251d7c5e01.md>)

Recorded evaluation configuration: {"Scale":"×8","Trainable parameters":"22.02M"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.