# Turntable Video Generation on GSO and Objaverse 200 meshes (test)

Source: [Turntable Video Generation on GSO and Objaverse 200 meshes (test)](<https://www.sota2.com/research/sota/turntable-video-generation-on-gso-and-objaverse-200-meshes-test>)

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

Data updated: 2026-03-19T09:54:33.650Z

Evaluation of models generating turntable videos of 3D assets, tested on the combined GSO and Objaverse 200 meshes test split, using video quality metrics like PSNR, SSIM, LPIPS, and FVD.

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 | Turntable Video Generation |
| Dataset (including any stated split) | GSO and Objaverse 200 meshes (test) |
| Metric | PSNR |
| 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

- [PSNR](<https://www.sota2.com/research/sota/turntable-video-generation-on-gso-and-objaverse-200-meshes-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/turntable-video-generation-on-gso-and-objaverse-200-meshes-test.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [LPIPS](<https://www.sota2.com/research/sota/turntable-video-generation-on-gso-and-objaverse-200-meshes-test.md?metric=LPIPS>): Lower is better; unit: PERCENT.

- [FVD](<https://www.sota2.com/research/sota/turntable-video-generation-on-gso-and-objaverse-200-meshes-test.md?metric=FVD>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| TAPESTRY | 25.79 | Not recorded | 69bb83020636e5bf4afc199b |
| Wan2.1-Fun | 24.32 | Not recorded | 69bb83020636e5bf4afc199b |
| Wan2.1-Fun | 23.48 | Not recorded | 69bb83020636e5bf4afc199b |
| Diffusion as Shader | 23.21 | Not recorded | 69bb83020636e5bf4afc199b |

### TAPESTRY

PSNR: 25.79. Result ID: 69bbc7d247f34ce924a62cc5.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83020636e5bf4afc199b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bb83020636e5bf4afc199b.md>)

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

### Wan2.1-Fun

PSNR: 24.32. Result ID: 69bbc7d247f34ce924a62cc3.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83020636e5bf4afc199b.md>)

Recorded evaluation configuration: {"Conditioning":"Canny"}. This record does not assert independent reproduction.

### Wan2.1-Fun

PSNR: 23.48. Result ID: 69bbc7d247f34ce924a62cc2.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83020636e5bf4afc199b.md>)

Recorded evaluation configuration: {"Conditioning":"Depth"}. This record does not assert independent reproduction.

### Diffusion as Shader

PSNR: 23.21. Result ID: 69bbc7d247f34ce924a62cc4.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83020636e5bf4afc199b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76901e209131cea6dbe9.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.
