# Video-driven Talking Head Generation on User Study 30 clips (test)

Source: [Video-driven Talking Head Generation on User Study 30 clips (test)](<https://www.sota2.com/research/sota/video-driven-talking-head-generation-on-user-study-30-clips-test>)

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

Data updated: 2026-02-26T05:46:58.206Z

Human evaluation benchmark for Video-driven Talking Head Generation models tested on the 'User Study 30 clips (test)' set, assessing Identity Preservation, Visual Quality, and Lip Synchronization.

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 | Video-driven Talking Head Generation |
| Dataset (including any stated split) | User Study 30 clips (test) |
| Metric | Identity Preservation |
| Unit | PERCENT |
| 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

- [Identity Preservation](<https://www.sota2.com/research/sota/video-driven-talking-head-generation-on-user-study-30-clips-test.md?metric=Identity%20Preservation>): Higher is better; unit: PERCENT.

- [Visual Quality](<https://www.sota2.com/research/sota/video-driven-talking-head-generation-on-user-study-30-clips-test.md?metric=Visual%20Quality>): Higher is better; unit: PERCENT.

- [Lip Synchronization](<https://www.sota2.com/research/sota/video-driven-talking-head-generation-on-user-study-30-clips-test.md?metric=Lip%20Synchronization>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Identity Preservation | Result date | Report paper |
| --- | --- | --- | --- |
| MGGTalk | 45 | Not recorded | 68fa77b31e209131cea74d69 |
| Portrait4D-v2 | 35 | Not recorded | 68fa77b31e209131cea74d69 |
| Others | 15 | Not recorded | 68fa77b31e209131cea74d69 |
| DaGAN | 5 | Not recorded | 68fa77b31e209131cea74d69 |

### MGGTalk

Identity Preservation: 45. Result ID: 69955f823badfaffe651ab00.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b31e209131cea74d69.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b31e209131cea74d69.md>)

[Implementation](<https://scut-mmpr.github.io/MGGTalk-Homepage/>)

Recorded evaluation configuration: {"Driven by":"Video"}. This record does not assert independent reproduction.

### Portrait4D-v2

Identity Preservation: 35. Result ID: 69955f823badfaffe651ab01.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b31e209131cea74d69.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73651e209131cea5c2f0.md>)

Recorded evaluation configuration: {"Driven by":"Video"}. This record does not assert independent reproduction.

### Others

Identity Preservation: 15. Result ID: 69955f823badfaffe651ab03.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b31e209131cea74d69.md>)

Recorded evaluation configuration: {"Driven by":"Video"}. This record does not assert independent reproduction.

### DaGAN

Identity Preservation: 5. Result ID: 69955f823badfaffe651ab02.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b31e209131cea74d69.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c011e209131cea31a14.md>)

[Implementation](<https://github.com/harlanhong/CVPR2022-DaGAN>)

Recorded evaluation configuration: {"Driven by":"Video"}. This record does not assert independent reproduction.

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