# Synthetic Image Generation on DEVICE-TEM synthetic

Source: [Synthetic Image Generation on DEVICE-TEM synthetic](<https://www.sota2.com/research/sota/synthetic-image-generation-on-device-tem-synthetic>)

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

Data updated: 2026-06-24T08:56:01.109Z

Evaluation of synthetic image generation models on the DEVICE-TEM synthetic dataset, measured using signal fidelity metrics including Noise standard deviation, Signal-to-Noise Ratio (SNR), and High-Frequency Noise Ratio (HFNR).

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 | Synthetic Image Generation |
| Dataset (including any stated split) | DEVICE-TEM synthetic |
| Metric | Noise Std |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 10 of 10 |
| 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

- [Noise Std](<https://www.sota2.com/research/sota/synthetic-image-generation-on-device-tem-synthetic.md?metric=Noise%20Std>): Lower is better; unit: SCALAR.

- [SNR](<https://www.sota2.com/research/sota/synthetic-image-generation-on-device-tem-synthetic.md?metric=SNR>): Higher is better; unit: SCALAR.

- [HFNR](<https://www.sota2.com/research/sota/synthetic-image-generation-on-device-tem-synthetic.md?metric=HFNR>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Noise Std | Result date | Report paper |
| --- | --- | --- | --- |
| MS-SSIM VAE | 0.008 | Not recorded | 6a3b64e7206542251d7c9a5e |
| MS-SSIM VAE | 0.009 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Original Data | 0.016 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Patch-based Progressive DDPM | 0.018 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Patch-based Progressive DDPM | 0.018 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Base DDPM | 0.018 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Base DDPM | 0.019 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Original Data | 0.022 | Not recorded | 6a3b64e7206542251d7c9a5e |
| DCGAN | 0.05 | Not recorded | 6a3b64e7206542251d7c9a5e |
| DCGAN | 0.052 | Not recorded | 6a3b64e7206542251d7c9a5e |

### MS-SSIM VAE

Noise Std: 0.008. Result ID: 6a3b9b95fbc373592c450cbc.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63171e209131ce9fc94c.md>)

Recorded evaluation configuration: {"Stat":"med."}. This record does not assert independent reproduction.

### MS-SSIM VAE

Noise Std: 0.009. Result ID: 6a3b9b95fbc373592c450cbb.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63171e209131ce9fc94c.md>)

Recorded evaluation configuration: {"Stat":"mean"}. This record does not assert independent reproduction.

### Original Data

Noise Std: 0.016. Result ID: 6a3b9b95fbc373592c450cb6.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"med."}. This record does not assert independent reproduction.

### Patch-based Progressive DDPM

Noise Std: 0.018. Result ID: 6a3b9b95fbc373592c450cb7.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"mean"}. This record does not assert independent reproduction.

### Patch-based Progressive DDPM

Noise Std: 0.018. Result ID: 6a3b9b95fbc373592c450cb8.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"med."}. This record does not assert independent reproduction.

### Base DDPM

Noise Std: 0.018. Result ID: 6a3b9b95fbc373592c450cba.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69151e209131cea20194.md>)

Recorded evaluation configuration: {"Stat":"med."}. This record does not assert independent reproduction.

### Base DDPM

Noise Std: 0.019. Result ID: 6a3b9b95fbc373592c450cb9.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69151e209131cea20194.md>)

Recorded evaluation configuration: {"Stat":"mean"}. This record does not assert independent reproduction.

### Original Data

Noise Std: 0.022. Result ID: 6a3b9b95fbc373592c450cb5.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"mean"}. This record does not assert independent reproduction.

### DCGAN

Noise Std: 0.05. Result ID: 6a3b9b95fbc373592c450cbe.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"med."}. This record does not assert independent reproduction.

### DCGAN

Noise Std: 0.052. Result ID: 6a3b9b95fbc373592c450cbd.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64e7206542251d7c9a5e.md>)

Recorded evaluation configuration: {"Stat":"mean"}. This record does not assert independent reproduction.

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