# Relighting on GS3 synthetic Lego (train)

Source: [Relighting on GS3 synthetic Lego (train)](<https://www.sota2.com/research/sota/relighting-on-gs3-synthetic-lego-train>)

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

Data updated: 2026-04-16T07:23:43.990Z

Evaluation of Relighting performance on the training split of the GS3 synthetic Lego dataset, measured using 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 | Relighting |
| Dataset (including any stated split) | GS3 synthetic Lego (train) |
| Metric | PSNR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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/relighting-on-gs3-synthetic-lego-train.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/relighting-on-gs3-synthetic-lego-train.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [LPIPS](<https://www.sota2.com/research/sota/relighting-on-gs3-synthetic-lego-train.md?metric=LPIPS>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| GS3 | 31.2224 | Not recorded | 69e06d1a7d0172140ec7caa8 |
| SSD-GS | 31.1434 | Not recorded | 69e06d1a7d0172140ec7caa8 |
| GI-GS | 19.5919 | Not recorded | 69e06d1a7d0172140ec7caa8 |
| 3DGS | 19.0612 | Not recorded | 69e06d1a7d0172140ec7caa8 |
| RNG | 18.581 | Not recorded | 69e06d1a7d0172140ec7caa8 |

### GS3

PSNR: 31.2224. Result ID: 69e08e6147f34ce924c96d12.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d1a7d0172140ec7caa8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75341e209131cea66649.md>)

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

### SSD-GS

PSNR: 31.1434. Result ID: 69e08e6147f34ce924c96d14.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d1a7d0172140ec7caa8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06d1a7d0172140ec7caa8.md>)

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

### GI-GS

PSNR: 19.5919. Result ID: 69e08e6147f34ce924c96d11.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d1a7d0172140ec7caa8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea74931.md>)

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

### 3DGS

PSNR: 19.0612. Result ID: 69e08e6147f34ce924c96d10.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d1a7d0172140ec7caa8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70461e209131cea4a191.md>)

[Implementation](<https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/>)

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

### RNG

PSNR: 18.581. Result ID: 69e08e6147f34ce924c96d13.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d1a7d0172140ec7caa8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77df1e209131cea75ba0.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.
