# Synthetic Image Generation on NANO-TEM (synthetic)

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

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

Data updated: 2026-06-24T08:56:01.079Z

Evaluation of synthetic image generation models on the NANO-TEM dataset, measured using metrics like Noise std, SNR, and 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) | NANO-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-nano-tem-synthetic.md?metric=Noise%20std>): Lower is better; unit: SCALAR.

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

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

## Recorded results

| Method | Noise std | Result date | Report paper |
| --- | --- | --- | --- |
| MS-SSIM VAE | 0.015 | Not recorded | 6a3b64e7206542251d7c9a5e |
| MS-SSIM VAE | 0.019 | Not recorded | 6a3b64e7206542251d7c9a5e |
| DCGAN | 0.026 | Not recorded | 6a3b64e7206542251d7c9a5e |
| patch-based progressive training methodology for DDPMs | 0.028 | Not recorded | 6a3b64e7206542251d7c9a5e |
| patch-based progressive training methodology for DDPMs | 0.028 | Not recorded | 6a3b64e7206542251d7c9a5e |
| DCGAN | 0.035 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Original (Target Distribution) | 0.037 | Not recorded | 6a3b64e7206542251d7c9a5e |
| Original (Target Distribution) | 0.041 | Not recorded | 6a3b64e7206542251d7c9a5e |
| DDPM Baseline | 0.043 | Not recorded | 6a3b64e7206542251d7c9a5e |
| DDPM Baseline | 0.043 | Not recorded | 6a3b64e7206542251d7c9a5e |

### MS-SSIM VAE

Noise std: 0.015. Result ID: 6a3b9b95fbc373592c450cb2.

[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: 0.019. Result ID: 6a3b9b95fbc373592c450cb1.

[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.

### DCGAN

Noise std: 0.026. Result ID: 6a3b9b95fbc373592c450cb4.

[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 training methodology for DDPMs

Noise std: 0.028. Result ID: 6a3b9b95fbc373592c450cad.

[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 training methodology for DDPMs

Noise std: 0.028. Result ID: 6a3b9b95fbc373592c450cae.

[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.

### DCGAN

Noise std: 0.035. Result ID: 6a3b9b95fbc373592c450cb3.

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

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

### Original (Target Distribution)

Noise std: 0.037. Result ID: 6a3b9b95fbc373592c450cac.

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

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

### Original (Target Distribution)

Noise std: 0.041. Result ID: 6a3b9b95fbc373592c450cab.

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

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

### DDPM Baseline

Noise std: 0.043. Result ID: 6a3b9b95fbc373592c450caf.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa68ef1e209131cea1f0d5.md>)

[Implementation](<https://github.com/hojonathanho/diffusion>)

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

### DDPM Baseline

Noise std: 0.043. Result ID: 6a3b9b95fbc373592c450cb0.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa68ef1e209131cea1f0d5.md>)

[Implementation](<https://github.com/hojonathanho/diffusion>)

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

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