# Camera-controlled video generation on SpatialVID extreme

Source: [Camera-controlled video generation on SpatialVID extreme](<https://www.sota2.com/research/sota/camera-controlled-video-generation-on-spatialvid-extreme>)

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

Data updated: 2026-02-26T05:58:02.484Z

Evaluation of models generating videos under camera control constraints using the SpatialVID extreme dataset, assessed using geometric error metrics (PitchErr, RotErr, TransErr) and generative quality metrics (FID, FVD, CLIP).

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 | Camera-controlled video generation |
| Dataset (including any stated split) | SpatialVID extreme |
| Metric | PitchErr (abs) |
| 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

- [PitchErr (abs)](<https://www.sota2.com/research/sota/camera-controlled-video-generation-on-spatialvid-extreme.md?metric=PitchErr%20(abs)>): Lower is better; unit: SCALAR.

- [GravityErr (abs)](<https://www.sota2.com/research/sota/camera-controlled-video-generation-on-spatialvid-extreme.md?metric=GravityErr%20(abs)>): Lower is better; unit: SCALAR.

- [RotErr (rel)](<https://www.sota2.com/research/sota/camera-controlled-video-generation-on-spatialvid-extreme.md?metric=RotErr%20(rel)>): Lower is better; unit: SCALAR.

- [TransErr](<https://www.sota2.com/research/sota/camera-controlled-video-generation-on-spatialvid-extreme.md?metric=TransErr>): Lower is better; unit: SCALAR.

- [CLIP](<https://www.sota2.com/research/sota/camera-controlled-video-generation-on-spatialvid-extreme.md?metric=CLIP>): Higher is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/camera-controlled-video-generation-on-spatialvid-extreme.md?metric=FID>): Lower is better; unit: SCALAR.

- [FVD](<https://www.sota2.com/research/sota/camera-controlled-video-generation-on-spatialvid-extreme.md?metric=FVD>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PitchErr (abs) | Result date | Report paper |
| --- | --- | --- | --- |
| GIMBALDIFFUSION | 23.79 | Not recorded | 693a501e6cfd488761a54b29 |
| PreciseCam + WAN-I2V-CC | 30.88 | Not recorded | 693a501e6cfd488761a54b29 |
| AC3D + cam. text. + abs. Plucker | 39.31 | Not recorded | 693a501e6cfd488761a54b29 |
| AC3D + cam. text. | 41.65 | Not recorded | 693a501e6cfd488761a54b29 |

### GIMBALDIFFUSION

PitchErr (abs): 23.79. Result ID: 6998695b5698665ec4c8d443.

[Reporting paper](<https://www.sota2.com/research/paper/693a501e6cfd488761a54b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/693a501e6cfd488761a54b29.md>)

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

### PreciseCam + WAN-I2V-CC

PitchErr (abs): 30.88. Result ID: 6998695b5698665ec4c8d442.

[Reporting paper](<https://www.sota2.com/research/paper/693a501e6cfd488761a54b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a81e209131cea6e3e1.md>)

Recorded evaluation configuration: {"model\_combination":"PreciseCam + WAN-I2V-CC"}. This record does not assert independent reproduction.

### AC3D + cam. text. + abs. Plucker

PitchErr (abs): 39.31. Result ID: 6998695b5698665ec4c8d441.

[Reporting paper](<https://www.sota2.com/research/paper/693a501e6cfd488761a54b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78681e209131cea7848a.md>)

[Implementation](<https://snap-research.github.io/ac3d>)

Recorded evaluation configuration: {"conditioning":"camera text","representation":"abs. Plucker"}. This record does not assert independent reproduction.

### AC3D + cam. text.

PitchErr (abs): 41.65. Result ID: 6998695b5698665ec4c8d440.

[Reporting paper](<https://www.sota2.com/research/paper/693a501e6cfd488761a54b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78681e209131cea7848a.md>)

[Implementation](<https://snap-research.github.io/ac3d>)

Recorded evaluation configuration: {"conditioning":"camera text"}. This record does not assert independent reproduction.

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