# Driving Scene Synthesis on Waymo (test)

Source: [Driving Scene Synthesis on Waymo (test)](<https://www.sota2.com/research/sota/driving-scene-synthesis-on-waymo-test>)

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

Data updated: 2026-05-12T12:04:40.375Z

Evaluation of driving scene synthesis models on the Waymo test split, focusing on geometric accuracy (RMSE, L1 Error), semantic alignment (mIoU, F1 Score), and perceptual similarity (CLIP-CMMD).

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 | Driving Scene Synthesis |
| Dataset (including any stated split) | Waymo (test) |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [mIoU](<https://www.sota2.com/research/sota/driving-scene-synthesis-on-waymo-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

- [RMSE](<https://www.sota2.com/research/sota/driving-scene-synthesis-on-waymo-test.md?metric=RMSE>): Lower is better; unit: SCALAR.

- [L1 Error](<https://www.sota2.com/research/sota/driving-scene-synthesis-on-waymo-test.md?metric=L1%20Error>): Lower is better; unit: SCALAR.

- [F1 Score](<https://www.sota2.com/research/sota/driving-scene-synthesis-on-waymo-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [CLIP-CMMD](<https://www.sota2.com/research/sota/driving-scene-synthesis-on-waymo-test.md?metric=CLIP-CMMD>): Lower is better; unit: SCALAR.

- [1 - MS-SSIM](<https://www.sota2.com/research/sota/driving-scene-synthesis-on-waymo-test.md?metric=1%20-%20MS-SSIM>): Lower is better; unit: SCALAR.

- [R-Precision@1](<https://www.sota2.com/research/sota/driving-scene-synthesis-on-waymo-test.md?metric=R-Precision%401>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| DGInStyle | 37.22 | Not recorded | 6a02b468dbc836b87d824b0f |
| PAM60K | 33.1 | Not recorded | 6a02b468dbc836b87d824b0f |
| Tune60K | 31.15 | Not recorded | 6a02b468dbc836b87d824b0f |

### DGInStyle

mIoU: 37.22. Result ID: 6a03174147f34ce924e71eec.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b468dbc836b87d824b0f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74541e209131cea611e7.md>)

[Implementation](<https://www.sota2.com/dginstyle.github.io>)

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

### PAM60K

mIoU: 33.1. Result ID: 6a03174147f34ce924e71eea.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b468dbc836b87d824b0f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b468dbc836b87d824b0f.md>)

Recorded evaluation configuration: {"Method":"Patch-wise Adaptation Module (PAM)","Training Steps":"60K"}. This record does not assert independent reproduction.

### Tune60K

mIoU: 31.15. Result ID: 6a03174147f34ce924e71eeb.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b468dbc836b87d824b0f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b468dbc836b87d824b0f.md>)

Recorded evaluation configuration: {"Method":"Fine-tuned Model","Training Steps":"60K"}. This record does not assert independent reproduction.

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