# Super-Resolution on ImageNet 256x256 Average-pooling sigma\_y=0 2012 (test)

Source: [Super-Resolution on ImageNet 256x256 Average-pooling sigma\_y=0 2012 (test)](<https://www.sota2.com/research/sota/super-resolution-on-imagenet-256x256-average-pooling-sigma_y-0-2012-test>)

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

Data updated: 2026-02-26T05:55:40.463Z

Evaluation of Super-Resolution models on the test split of ImageNet, specifically using images rendered at 256x256 resolution degraded via average pooling with sigma\_y=0, based on the 2012 setup.

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 | Super-Resolution |
| Dataset (including any stated split) | ImageNet 256x256 Average-pooling sigma\_y=0 2012 (test) |
| Metric | PSNR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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](<https://www.sota2.com/research/sota/super-resolution-on-imagenet-256x256-average-pooling-sigma_y-0-2012-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/super-resolution-on-imagenet-256x256-average-pooling-sigma_y-0-2012-test.md?metric=SSIM>): Higher is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/super-resolution-on-imagenet-256x256-average-pooling-sigma_y-0-2012-test.md?metric=FID>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| DDNM | 27.04 | Not recorded | 68fa6e201e209131cea3dfb9 |
| BSRGAN | 24.14 | Not recorded | 68fa6e201e209131cea3dfb9 |
| SwinIR-L | 23.88 | Not recorded | 68fa6e201e209131cea3dfb9 |

### DDNM

PSNR: 27.04. Result ID: 699005ab3a6c314849fd88ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e201e209131cea3dfb9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e201e209131cea3dfb9.md>)

[Implementation](<https://github.com/wyhuai/DDNM>)

Recorded evaluation configuration: {"Inference time":"11.9 s/image","DDIM steps":100,"eta":0.85,"Classifier guidance":"false","zero-shot":"true"}. This record does not assert independent reproduction.

### BSRGAN

PSNR: 24.14. Result ID: 699005ab3a6c314849fd88fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e201e209131cea3dfb9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af01e209131cea2b36c.md>)

[Implementation](<https://github.com/cszn/BSRGAN>)

Recorded evaluation configuration: {"Inference time":"0.036 s/image","Pre-trained":"true"}. This record does not assert independent reproduction.

### SwinIR-L

PSNR: 23.88. Result ID: 699005ab3a6c314849fd88fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e201e209131cea3dfb9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a9a1e209131cea294aa.md>)

[Implementation](<https://github.com/JingyunLiang/SwinIR>)

Recorded evaluation configuration: {"Inference time":"6.1 s/image","Pre-trained":"true"}. This record does not assert independent reproduction.

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