# Video Generation on nuScenes 16-second videos (test)

Source: [Video Generation on nuScenes 16-second videos (test)](<https://www.sota2.com/research/sota/video-generation-on-nuscenes-16-second-videos-test>)

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

Data updated: 2026-03-27T12:29:38.634Z

Evaluation of video generation models on the 16-second test split of the nuScenes dataset, utilizing temporal fidelity metrics (FID/FVD across 4-second intervals) alongside ATE and ARE.

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 Generation |
| Dataset (including any stated split) | nuScenes 16-second videos (test) |
| Metric | Overall FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 6 of 6 |
| 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

- [Overall FID](<https://www.sota2.com/research/sota/video-generation-on-nuscenes-16-second-videos-test.md?metric=Overall%20FID>): Lower is better; unit: SCALAR.

- [Overall FVD](<https://www.sota2.com/research/sota/video-generation-on-nuscenes-16-second-videos-test.md?metric=Overall%20FVD>): Lower is better; unit: SCALAR.

- [FID (0-4 s)](<https://www.sota2.com/research/sota/video-generation-on-nuscenes-16-second-videos-test.md?metric=FID%20(0-4%20s)>): Lower is better; unit: SCALAR.

- [FVD (0-4 s)](<https://www.sota2.com/research/sota/video-generation-on-nuscenes-16-second-videos-test.md?metric=FVD%20(0-4%20s)>): Lower is better; unit: SCALAR.

- [FID (4-8 s)](<https://www.sota2.com/research/sota/video-generation-on-nuscenes-16-second-videos-test.md?metric=FID%20(4-8%20s)>): Lower is better; unit: SCALAR.

- [FVD (4-8 s)](<https://www.sota2.com/research/sota/video-generation-on-nuscenes-16-second-videos-test.md?metric=FVD%20(4-8%20s)>): Lower is better; unit: SCALAR.

- [FID (8-12 s)](<https://www.sota2.com/research/sota/video-generation-on-nuscenes-16-second-videos-test.md?metric=FID%20(8-12%20s)>): Lower is better; unit: SCALAR.

- [FVD (8-12 s)](<https://www.sota2.com/research/sota/video-generation-on-nuscenes-16-second-videos-test.md?metric=FVD%20(8-12%20s)>): Lower is better; unit: SCALAR.

- [FID (12-16 s)](<https://www.sota2.com/research/sota/video-generation-on-nuscenes-16-second-videos-test.md?metric=FID%20(12-16%20s)>): Lower is better; unit: SCALAR.

- [FVD (12-16 s)](<https://www.sota2.com/research/sota/video-generation-on-nuscenes-16-second-videos-test.md?metric=FVD%20(12-16%20s)>): Lower is better; unit: SCALAR.

- [ATE](<https://www.sota2.com/research/sota/video-generation-on-nuscenes-16-second-videos-test.md?metric=ATE>): Lower is better; unit: SCALAR.

- [ARE](<https://www.sota2.com/research/sota/video-generation-on-nuscenes-16-second-videos-test.md?metric=ARE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Overall FID | Result date | Report paper |
| --- | --- | --- | --- |
| DCARL | 19.6 | Not recorded | 69c60ee50636e5bf4afc8386 |
| SEVA | 35.9 | Not recorded | 69c60ee50636e5bf4afc8386 |
| DiffF | 37.1 | Not recorded | 69c60ee50636e5bf4afc8386 |
| DeepF | 50.3 | Not recorded | 69c60ee50636e5bf4afc8386 |
| SelfF | 53.1 | Not recorded | 69c60ee50636e5bf4afc8386 |
| Vista | 68.7 | Not recorded | 69c60ee50636e5bf4afc8386 |

### DCARL

Overall FID: 19.6. Result ID: 69c6782247f34ce924b048d3.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee50636e5bf4afc8386.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60ee50636e5bf4afc8386.md>)

Recorded evaluation configuration: {"zero-shot":"true","video duration":"16s"}. This record does not assert independent reproduction.

### SEVA

Overall FID: 35.9. Result ID: 69c6782247f34ce924b048d2.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee50636e5bf4afc8386.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77c51e209131cea7536c.md>)

Recorded evaluation configuration: {"zero-shot":"true","video duration":"16s"}. This record does not assert independent reproduction.

### DiffF

Overall FID: 37.1. Result ID: 69c6782247f34ce924b048ce.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee50636e5bf4afc8386.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa762a1e209131cea6b9aa.md>)

Recorded evaluation configuration: {"zero-shot":"true","video duration":"16s"}. This record does not assert independent reproduction.

### DeepF

Overall FID: 50.3. Result ID: 69c6782247f34ce924b048d0.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee50636e5bf4afc8386.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6932675bd6b0dd3342934580.md>)

Recorded evaluation configuration: {"zero-shot":"true","video duration":"16s"}. This record does not assert independent reproduction.

### SelfF

Overall FID: 53.1. Result ID: 69c6782247f34ce924b048cf.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee50636e5bf4afc8386.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa793a1e209131cea7cb5a.md>)

Recorded evaluation configuration: {"zero-shot":"true","video duration":"16s"}. This record does not assert independent reproduction.

### Vista

Overall FID: 68.7. Result ID: 69c6782247f34ce924b048d1.

[Reporting paper](<https://www.sota2.com/research/paper/69c60ee50636e5bf4afc8386.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756e1e209131cea67df9.md>)

Recorded evaluation configuration: {"zero-shot":"true","video duration":"16s"}. This record does not assert independent reproduction.

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