# Human Pose Recommendation on CaptureGuide-Bench subject-side guidance

Source: [Human Pose Recommendation on CaptureGuide-Bench subject-side guidance](<https://www.sota2.com/research/sota/human-pose-recommendation-on-captureguide-bench-subject-side-guidance>)

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

Data updated: 2026-06-25T08:38:48.089Z

Evaluation of models generating recommended human poses based on the CaptureGuide-Bench subject-side guidance data, assessed using metrics like Plausibility, Interaction, and Aesthetics.

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 | Human Pose Recommendation |
| Dataset (including any stated split) | CaptureGuide-Bench subject-side guidance |
| Metric | Plausibility |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Plausibility](<https://www.sota2.com/research/sota/human-pose-recommendation-on-captureguide-bench-subject-side-guidance.md?metric=Plausibility>): Higher is better; unit: PERCENT.

- [Interaction](<https://www.sota2.com/research/sota/human-pose-recommendation-on-captureguide-bench-subject-side-guidance.md?metric=Interaction>): Higher is better; unit: PERCENT.

- [Aesthetics](<https://www.sota2.com/research/sota/human-pose-recommendation-on-captureguide-bench-subject-side-guidance.md?metric=Aesthetics>): Higher is better; unit: PERCENT.

- [Mean Score](<https://www.sota2.com/research/sota/human-pose-recommendation-on-captureguide-bench-subject-side-guidance.md?metric=Mean%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Plausibility | Result date | Report paper |
| --- | --- | --- | --- |
| Nano-Banana-Pro | 63 | Not recorded | 6a3cb624206542251d7ca624 |
| GPT-Image-2 | 59 | Not recorded | 6a3cb624206542251d7ca624 |
| ShutterMuse | 58 | Not recorded | 6a3cb624206542251d7ca624 |

### Nano-Banana-Pro

Plausibility: 63. Result ID: 6a3ce905fbc373592c528474.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb624206542251d7ca624.md>)

Recorded evaluation configuration: {"Organization":"Google","Time":"55.16","# Tokens":"1370"}. This record does not assert independent reproduction.

### GPT-Image-2

Plausibility: 59. Result ID: 6a3ce905fbc373592c528475.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb624206542251d7ca624.md>)

Recorded evaluation configuration: {"Organization":"OpenAI","Time":"102.61","# Tokens":"1427"}. This record does not assert independent reproduction.

### ShutterMuse

Plausibility: 58. Result ID: 6a3ce905fbc373592c528476.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb624206542251d7ca624.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3cb624206542251d7ca624.md>)

[Implementation](<https://github.com/lijayuTnT/ShutterMuse>)

Recorded evaluation configuration: {"Time":"4.96","# Tokens":"412"}. This record does not assert independent reproduction.

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