# Low-dose image synthesis on Synthesized 10% dose images (test)

Source: [Low-dose image synthesis on Synthesized 10% dose images (test)](<https://www.sota2.com/research/sota/low-dose-image-synthesis-on-synthesized-10-percent-dose-images-test>)

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

Data updated: 2026-02-26T05:55:50.072Z

Evaluation of image synthesis models specifically designed for low-dose scenarios, tested on the 'Synthesized 10% dose images' test set, measured using fidelity metrics such as PSNR, SSIM, RMSE, and LPIPS.

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 | Low-dose image synthesis |
| Dataset (including any stated split) | Synthesized 10% dose images (test) |
| Metric | PSNR |
| 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](<https://www.sota2.com/research/sota/low-dose-image-synthesis-on-synthesized-10-percent-dose-images-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/low-dose-image-synthesis-on-synthesized-10-percent-dose-images-test.md?metric=SSIM>): Higher is better; unit: SCALAR.

- [RMSE](<https://www.sota2.com/research/sota/low-dose-image-synthesis-on-synthesized-10-percent-dose-images-test.md?metric=RMSE>): Lower is better; unit: SCALAR.

- [LPIPS](<https://www.sota2.com/research/sota/low-dose-image-synthesis-on-synthesized-10-percent-dose-images-test.md?metric=LPIPS>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| Gformer | 42.29 | Not recorded | 68fa701b1e209131cea4910d |
| Gformer | 41.46 | Not recorded | 68fa701b1e209131cea4910d |
| SwinIR | 40.93 | Not recorded | 68fa701b1e209131cea4910d |
| Mapnn | 40.56 | Not recorded | 68fa701b1e209131cea4910d |
| Rednet | 40.07 | Not recorded | 68fa701b1e209131cea4910d |
| Restormer | 40.04 | Not recorded | 68fa701b1e209131cea4910d |
| Scaling | 38.41 | Not recorded | 68fa701b1e209131cea4910d |
| Post | 33.93 | Not recorded | 68fa701b1e209131cea4910d |

### Gformer

PSNR: 42.29. Result ID: 69910a4d3a6c3148490539e1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701b1e209131cea4910d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701b1e209131cea4910d.md>)

Recorded evaluation configuration: {"variant":"rotational shift (Rot)","Throughput":"0.65 Im/s"}. This record does not assert independent reproduction.

### Gformer

PSNR: 41.46. Result ID: 69910a4d3a6c3148490539e0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701b1e209131cea4910d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701b1e209131cea4910d.md>)

Recorded evaluation configuration: {"variant":"cyclic shift (Cyc)","Throughput":"0.69 Im/s"}. This record does not assert independent reproduction.

### SwinIR

PSNR: 40.93. Result ID: 69910a4d3a6c3148490539df.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701b1e209131cea4910d.md>)

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

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

Recorded evaluation configuration: {"Throughput":"0.58 Im/s"}. This record does not assert independent reproduction.

### Mapnn

PSNR: 40.56. Result ID: 69910a4d3a6c3148490539dd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701b1e209131cea4910d.md>)

Recorded evaluation configuration: {"Throughput":"0.71 Im/s"}. This record does not assert independent reproduction.

### Rednet

PSNR: 40.07. Result ID: 69910a4d3a6c3148490539dc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701b1e209131cea4910d.md>)

Recorded evaluation configuration: {"Throughput":"0.71 Im/s"}. This record does not assert independent reproduction.

### Restormer

PSNR: 40.04. Result ID: 69910a4d3a6c3148490539de.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701b1e209131cea4910d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bfc1e209131cea316e3.md>)

[Implementation](<https://github.com/swz30/Restormer>)

Recorded evaluation configuration: {"Throughput":"0.65 Im/s"}. This record does not assert independent reproduction.

### Scaling

PSNR: 38.41. Result ID: 69910a4d3a6c3148490539db.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701b1e209131cea4910d.md>)

Recorded evaluation configuration: {"Throughput":"0.79 Im/s"}. This record does not assert independent reproduction.

### Post

PSNR: 33.93. Result ID: 69910a4d3a6c3148490539da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701b1e209131cea4910d.md>)

Recorded evaluation configuration: {"Throughput":null}. This record does not assert independent reproduction.

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