# Realism Assessment on In-house real endoscopy image dataset

Source: [Realism Assessment on In-house real endoscopy image dataset](<https://www.sota2.com/research/sota/realism-assessment-on-in-house-real-endoscopy-image-dataset>)

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

Data updated: 2026-02-26T05:44:29.636Z

Evaluation of image realism assessment performance on an in-house dataset of real endoscopy images, typically measured using distribution similarity metrics like FID and KID.

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 | Realism Assessment |
| Dataset (including any stated split) | In-house real endoscopy image dataset |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| 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

- [FID](<https://www.sota2.com/research/sota/realism-assessment-on-in-house-real-endoscopy-image-dataset.md?metric=FID>): Lower is better; unit: SCALAR.

- [KID](<https://www.sota2.com/research/sota/realism-assessment-on-in-house-real-endoscopy-image-dataset.md?metric=KID>): Lower is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| I2I | 106.8 | Not recorded | 68fa74c61e209131cea63b94 |
| MeshBrush | 187.1 | Not recorded | 68fa74c61e209131cea63b94 |
| MeshBrush | 206.1 | Not recorded | 68fa74c61e209131cea63b94 |
| Untextured | 240.9 | Not recorded | 68fa74c61e209131cea63b94 |
| MeshBrush | 246.5 | Not recorded | 68fa74c61e209131cea63b94 |

### I2I

FID: 106.8. Result ID: 699367073a6c31484915ae29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c61e209131cea63b94.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65fe1e209131cea0dce6.md>)

Recorded evaluation configuration: {"Type":"Independently processed style transfers"}. This record does not assert independent reproduction.

### MeshBrush

FID: 187.1. Result ID: 699367073a6c31484915ae2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c61e209131cea63b94.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c61e209131cea63b94.md>)

[Implementation](<https://www.slicer.org/>)

Recorded evaluation configuration: {"Heatmap":"Removed"}. This record does not assert independent reproduction.

### MeshBrush

FID: 206.1. Result ID: 699367073a6c31484915ae2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c61e209131cea63b94.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c61e209131cea63b94.md>)

[Implementation](<https://www.slicer.org/>)

Recorded evaluation configuration: {"Configuration":"Default"}. This record does not assert independent reproduction.

### Untextured

FID: 240.9. Result ID: 699367073a6c31484915ae28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c61e209131cea63b94.md>)

Recorded evaluation configuration: {"Type":"Renders from mesh without style transfer"}. This record does not assert independent reproduction.

### MeshBrush

FID: 246.5. Result ID: 699367073a6c31484915ae2c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c61e209131cea63b94.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c61e209131cea63b94.md>)

[Implementation](<https://www.slicer.org/>)

Recorded evaluation configuration: {"Heatmap":"Removed","Fourier Components":"Removed"}. This record does not assert independent reproduction.

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