# Multi-view video synthesis on VBench View 2

Source: [Multi-view video synthesis on VBench View 2](<https://www.sota2.com/research/sota/multi-view-video-synthesis-on-vbench-view-2>)

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

Data updated: 2026-03-20T09:53:39.077Z

Evaluation of Multi-view Video Synthesis models using the VBench View 2 dataset, assessed across key perceptual dimensions such as motion, subject consistency, and image quality.

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 | Multi-view video synthesis |
| Dataset (including any stated split) | VBench View 2 |
| Metric | Motion Score |
| Unit | SCALAR |
| 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

- [Motion Score](<https://www.sota2.com/research/sota/multi-view-video-synthesis-on-vbench-view-2.md?metric=Motion%20Score>): Higher is better; unit: SCALAR.

- [Subject Consistency Score](<https://www.sota2.com/research/sota/multi-view-video-synthesis-on-vbench-view-2.md?metric=Subject%20Consistency%20Score>): Higher is better; unit: SCALAR.

- [Image Quality Score](<https://www.sota2.com/research/sota/multi-view-video-synthesis-on-vbench-view-2.md?metric=Image%20Quality%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Motion Score | Result date | Report paper |
| --- | --- | --- | --- |
| Phys4View | 0.994 | Not recorded | 69bcd49b0636e5bf4afc2a6f |
| L4GM | 0.992 | Not recorded | 69bcd49b0636e5bf4afc2a6f |
| DG4D | 0.987 | Not recorded | 69bcd49b0636e5bf4afc2a6f |
| Diffusion² | 0.979 | Not recorded | 69bcd49b0636e5bf4afc2a6f |

### Phys4View

Motion Score: 0.994. Result ID: 69bd18d847f34ce924a7a23e.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd49b0636e5bf4afc2a6f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bcd49b0636e5bf4afc2a6f.md>)

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

### L4GM

Motion Score: 0.992. Result ID: 69bd18d847f34ce924a7a23d.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd49b0636e5bf4afc2a6f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73b31e209131cea5e003.md>)

[Implementation](<https://research.nvidia.com/labs/toronto-ai/l4gm>)

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

### DG4D

Motion Score: 0.987. Result ID: 69bd18d847f34ce924a7a23b.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd49b0636e5bf4afc2a6f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73851e209131cea5ce9b.md>)

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

### Diffusion²

Motion Score: 0.979. Result ID: 69bd18d847f34ce924a7a23c.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd49b0636e5bf4afc2a6f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75091e209131cea65724.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.
