# Scene Hallucination on Video-based human insertion dataset 1.0 (test)

Source: [Scene Hallucination on Video-based human insertion dataset 1.0 (test)](<https://www.sota2.com/research/sota/scene-hallucination-on-video-based-human-insertion-dataset-1-0-test>)

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

Data updated: 2026-02-26T05:44:22.372Z

Evaluation of scene hallucination performance using the test split of the Video-based human insertion dataset 1.0, measured by FID.

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 | Scene Hallucination |
| Dataset (including any stated split) | Video-based human insertion dataset 1.0 (test) |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower 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

- [FID](<https://www.sota2.com/research/sota/scene-hallucination-on-video-based-human-insertion-dataset-1-0-test.md?metric=FID>): Lower is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| Ours | 20.268 | Not recorded | 68fa6f271e209131cea44150 |
| Stable Diffusion | 44.687 | Not recorded | 68fa6f271e209131cea44150 |

### Ours

FID: 20.268. Result ID: 699098dd3a6c31484901bed7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f271e209131cea44150.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f271e209131cea44150.md>)

[Implementation](<https://sumith1896.github.io/affordance-insertion>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Stable Diffusion

FID: 44.687. Result ID: 699098dd3a6c31484901bed6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f271e209131cea44150.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c391e209131cea32e4a.md>)

[Implementation](<https://github.com/CompVis/latent-diffusion>)

Recorded evaluation configuration: {"prompt":"a natural coherent image of a person in a scene."}. This record does not assert independent reproduction.

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