# Latent Factor Separation on FFHQ Head Pose: Frontal vs. Right/Left

Source: [Latent Factor Separation on FFHQ Head Pose: Frontal vs. Right/Left](<https://www.sota2.com/research/sota/latent-factor-separation-on-ffhq-head-pose-frontal-vs-right-left>)

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

Data updated: 2026-02-26T05:37:57.858Z

Evaluation of disentanglement capabilities for separating head pose factors (Frontal vs. Right/Left views) on the FFHQ dataset, measured using C, S, and Delta metrics.

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 | Latent Factor Separation |
| Dataset (including any stated split) | FFHQ Head Pose: Frontal vs. Right/Left |
| Metric | C Metric |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [C Metric](<https://www.sota2.com/research/sota/latent-factor-separation-on-ffhq-head-pose-frontal-vs-right-left.md?metric=C%20Metric>): Higher is better; unit: SCALAR.

- [S Metric](<https://www.sota2.com/research/sota/latent-factor-separation-on-ffhq-head-pose-frontal-vs-right-left.md?metric=S%20Metric>): Higher is better; unit: SCALAR.

- [Delta Metric](<https://www.sota2.com/research/sota/latent-factor-separation-on-ffhq-head-pose-frontal-vs-right-left.md?metric=Delta%20Metric>): Higher is better; unit: SCALAR.

## Recorded results

| Method | C Metric | Result date | Report paper |
| --- | --- | --- | --- |
| pSp-cs | 0.95 | Not recorded | 6940e7ce456146936284faed |
| MM-cVAE | 0.73 | Not recorded | 6940e7ce456146936284faed |
| Double InfoGAN | 0.71 | Not recorded | 6940e7ce456146936284faed |
| SepVAE | 0.69 | Not recorded | 6940e7ce456146936284faed |

### pSp-cs

C Metric: 0.95. Result ID: 69984d065698665ec4aa6880.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

Recorded evaluation configuration: {"Backbone":"StyleGAN","Encoder":"pSp"}. This record does not assert independent reproduction.

### MM-cVAE

C Metric: 0.73. Result ID: 69984d065698665ec4aa687d.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bd71e209131cea307d2.md>)

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

### Double InfoGAN

C Metric: 0.71. Result ID: 69984d065698665ec4aa687f.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71fe1e209131cea53f84.md>)

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

### SepVAE

C Metric: 0.69. Result ID: 69984d065698665ec4aa687e.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7ce456146936284faed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d61e209131cea58d4d.md>)

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

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