# 3D-aware talking portrait generation on NeRSemble (novel views)

Source: [3D-aware talking portrait generation on NeRSemble (novel views)](<https://www.sota2.com/research/sota/3d-aware-talking-portrait-generation-on-nersemble-novel-views>)

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

Data updated: 2026-02-26T05:44:40.338Z

Evaluation of models generating 3D-aware talking portraits using the novel views subset of the NeRSemble dataset, assessed via fidelity (FID, FVD, LPIPS, SSIM, PSNR) 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 | 3D-aware talking portrait generation |
| Dataset (including any stated split) | NeRSemble (novel views) |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower 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

- [FID](<https://www.sota2.com/research/sota/3d-aware-talking-portrait-generation-on-nersemble-novel-views.md?metric=FID>): Lower is better; unit: SCALAR.

- [FVD](<https://www.sota2.com/research/sota/3d-aware-talking-portrait-generation-on-nersemble-novel-views.md?metric=FVD>): Lower is better; unit: SCALAR.

- [LPIPS](<https://www.sota2.com/research/sota/3d-aware-talking-portrait-generation-on-nersemble-novel-views.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/3d-aware-talking-portrait-generation-on-nersemble-novel-views.md?metric=SSIM>): Higher is better; unit: SCALAR.

- [PSNR](<https://www.sota2.com/research/sota/3d-aware-talking-portrait-generation-on-nersemble-novel-views.md?metric=PSNR>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| STARCaster | 29.52 | Not recorded | 6940e7b2456146936284f98c |
| Real3DPortrait | 32.33 | Not recorded | 6940e7b2456146936284f98c |
| Portrait4D-v2 | 48.91 | Not recorded | 6940e7b2456146936284f98c |
| GOHA | 85.63 | Not recorded | 6940e7b2456146936284f98c |

### STARCaster

FID: 29.52. Result ID: 699847b35698665ec4a49ad5.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7b2456146936284f98c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6940e7b2456146936284f98c.md>)

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

### Real3DPortrait

FID: 32.33. Result ID: 699847b35698665ec4a49ad4.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7b2456146936284f98c.md>)

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

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

### Portrait4D-v2

FID: 48.91. Result ID: 699847b35698665ec4a49ad3.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7b2456146936284f98c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74131e209131cea5fa9c.md>)

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

### GOHA

FID: 85.63. Result ID: 699847b35698665ec4a49ad2.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7b2456146936284f98c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fba1e209131cea4710d.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.