# Image Realism Classification on User Study dataset real vs. synthesized images

Source: [Image Realism Classification on User Study dataset real vs. synthesized images](<https://www.sota2.com/research/sota/image-realism-classification-on-user-study-dataset-real-vs-synthesized-images>)

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

Data updated: 2026-02-26T05:27:56.906Z

Evaluation of Image Realism Classification performance using the User Study dataset comparing real versus synthesized images.

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 | Image Realism Classification |
| Dataset (including any stated split) | User Study dataset real vs. synthesized images |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-realism-classification-on-user-study-dataset-real-vs-synthesized-images.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [False Positives Rate (FPR)](<https://www.sota2.com/research/sota/image-realism-classification-on-user-study-dataset-real-vs-synthesized-images.md?metric=False%20Positives%20Rate%20(FPR)>): Lower is better; unit: PERCENT.

- [False Negatives Rate (FNR)](<https://www.sota2.com/research/sota/image-realism-classification-on-user-study-dataset-real-vs-synthesized-images.md?metric=False%20Negatives%20Rate%20(FNR)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| OVNet | 65.5 | Not recorded | 68fa6a291e209131cea26795 |
| OVNet | 57.3 | Not recorded | 68fa6a291e209131cea26795 |

### OVNet

Accuracy: 65.5. Result ID: 698e1b39ffc3901de09ad82b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a291e209131cea26795.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a291e209131cea26795.md>)

Recorded evaluation configuration: {"Evaluator Group":"Researchers","Number of Participants":"19"}. This record does not assert independent reproduction.

### OVNet

Accuracy: 57.3. Result ID: 698e1b39ffc3901de09ad82a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a291e209131cea26795.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a291e209131cea26795.md>)

Recorded evaluation configuration: {"Evaluator Group":"Crowds","Number of Participants":"31"}. This record does not assert independent reproduction.

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