# Video-driven Talking Head Generation (Cross-Reenactment) on NeRSemble Mono

Source: [Video-driven Talking Head Generation (Cross-Reenactment) on NeRSemble Mono](<https://www.sota2.com/research/sota/video-driven-talking-head-generation-cross-reenactment-on-nersemble-mono>)

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

Data updated: 2026-02-26T05:44:33.455Z

Evaluation of Video-driven Talking Head Generation models focusing on cross-reenactment performance on the NeRSemble Mono dataset, measured using FID, AED, and APD.

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 (Cross-Reenactment) |
| Dataset (including any stated split) | NeRSemble Mono |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 7 of 7 |
| 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/video-driven-talking-head-generation-cross-reenactment-on-nersemble-mono.md?metric=FID>): Lower is better; unit: SCALAR.

- [AED](<https://www.sota2.com/research/sota/video-driven-talking-head-generation-cross-reenactment-on-nersemble-mono.md?metric=AED>): Lower is better; unit: SCALAR.

- [APD](<https://www.sota2.com/research/sota/video-driven-talking-head-generation-cross-reenactment-on-nersemble-mono.md?metric=APD>): Lower is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| MGGTalk | 57.82 | Not recorded | 68fa77b31e209131cea74d69 |
| Portrait4D-v2 | 63.97 | Not recorded | 68fa77b31e209131cea74d69 |
| OTAvatar | 73.3 | Not recorded | 68fa77b31e209131cea74d69 |
| Real3DPortrait | 88.91 | Not recorded | 68fa77b31e209131cea74d69 |
| Styleheat | 93.25 | Not recorded | 68fa77b31e209131cea74d69 |
| DaGAN | 108.12 | Not recorded | 68fa77b31e209131cea74d69 |
| ROME | 119.09 | Not recorded | 68fa77b31e209131cea74d69 |

### MGGTalk

FID: 57.82. Result ID: 69955f823badfaffe651aaff.

[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: Not recorded. This record does not assert independent reproduction.

### Portrait4D-v2

FID: 63.97. Result ID: 69955f823badfaffe651aafe.

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

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

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

### OTAvatar

FID: 73.3. Result ID: 69955f823badfaffe651aafc.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e0a.md>)

[Implementation](<https://github.com/theEricMa/OTAvatar>)

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

### Real3DPortrait

FID: 88.91. Result ID: 69955f823badfaffe651aafd.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa72a31e209131cea57ba3.md>)

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

### Styleheat

FID: 93.25. Result ID: 69955f823badfaffe651aaf9.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c151e209131cea32086.md>)

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

### DaGAN

FID: 108.12. Result ID: 69955f823badfaffe651aafa.

[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: Not recorded. This record does not assert independent reproduction.

### ROME

FID: 119.09. Result ID: 69955f823badfaffe651aafb.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cc11e209131cea35cd6.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.