# Scene-level Reconstruction on DL3DV 10K (test)

Source: [Scene-level Reconstruction on DL3DV 10K (test)](<https://www.sota2.com/research/sota/scene-level-reconstruction-on-dl3dv-10k-test>)

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

Data updated: 2026-02-26T05:56:18.246Z

Evaluation of Scene-level Reconstruction performance on the test split of the DL3DV 10K dataset, measured using photometric metrics like PSNR, SSIM, and LPIPS.

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 | Scene-level Reconstruction |
| Dataset (including any stated split) | DL3DV 10K (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/scene-level-reconstruction-on-dl3dv-10k-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/scene-level-reconstruction-on-dl3dv-10k-test.md?metric=SSIM>): Higher is better; unit: SCALAR.

- [LPIPS](<https://www.sota2.com/research/sota/scene-level-reconstruction-on-dl3dv-10k-test.md?metric=LPIPS>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| Generative Densification | 17.76 | Not recorded | 68fa77461e209131cea72251 |
| MVSplat-finetune | 17.42 | Not recorded | 68fa77461e209131cea72251 |
| Generative Densification | 16.46 | Not recorded | 68fa77461e209131cea72251 |
| MVSplat-finetune | 16.19 | Not recorded | 68fa77461e209131cea72251 |

### Generative Densification

PSNR: 17.76. Result ID: 69948f293a6c3148491e00d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77461e209131cea72251.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77461e209131cea72251.md>)

[Implementation](<https://stnamjef.github.io/GenerativeDensification/>)

Recorded evaluation configuration: {"frame distance span (n)":150}. This record does not assert independent reproduction.

### MVSplat-finetune

PSNR: 17.42. Result ID: 69948f293a6c3148491e00d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77461e209131cea72251.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa759f1e209131cea6907c.md>)

Recorded evaluation configuration: {"frame distance span (n)":150}. This record does not assert independent reproduction.

### Generative Densification

PSNR: 16.46. Result ID: 69948f293a6c3148491e00d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77461e209131cea72251.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77461e209131cea72251.md>)

[Implementation](<https://stnamjef.github.io/GenerativeDensification/>)

Recorded evaluation configuration: {"frame distance span (n)":300}. This record does not assert independent reproduction.

### MVSplat-finetune

PSNR: 16.19. Result ID: 69948f293a6c3148491e00d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77461e209131cea72251.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa759f1e209131cea6907c.md>)

Recorded evaluation configuration: {"frame distance span (n)":300}. This record does not assert independent reproduction.

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