# LiDAR Semantic Segmentation on SynLiDAR to SemanticSTF Transfer (test)

Source: [LiDAR Semantic Segmentation on SynLiDAR to SemanticSTF Transfer (test)](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test>)

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

Data updated: 2026-03-31T11:51:10.340Z

Evaluation of LiDAR Semantic Segmentation performance on the test split of the SynLiDAR to SemanticSTF Transfer benchmark, reporting class-specific Intersection over Union (IoU) metrics and overall mIoU.

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 | LiDAR Semantic Segmentation |
| Dataset (including any stated split) | SynLiDAR to SemanticSTF Transfer (test) |
| Metric | Car IoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Car IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Car%20IoU>): Higher is better; unit: PERCENT.

- [BI.CLE IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=BI.CLE%20IoU>): Higher is better; unit: PERCENT.

- [MT.CLE IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=MT.CLE%20IoU>): Higher is better; unit: PERCENT.

- [Truck IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Truck%20IoU>): Higher is better; unit: PERCENT.

- [Oth-V. IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Oth-V.%20IoU>): Higher is better; unit: PERCENT.

- [Pers. IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Pers.%20IoU>): Higher is better; unit: PERCENT.

- [BI.CLST IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=BI.CLST%20IoU>): Higher is better; unit: PERCENT.

- [MT.CLST IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=MT.CLST%20IoU>): Higher is better; unit: PERCENT.

- [Road IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Road%20IoU>): Higher is better; unit: PERCENT.

- [Parki. IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Parki.%20IoU>): Higher is better; unit: PERCENT.

- [Sidew. IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Sidew.%20IoU>): Higher is better; unit: PERCENT.

- [Othe.G. IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Othe.G.%20IoU>): Higher is better; unit: PERCENT.

- [Build. IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Build.%20IoU>): Higher is better; unit: PERCENT.

- [Fence IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Fence%20IoU>): Higher is better; unit: PERCENT.

- [Veget. IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Veget.%20IoU>): Higher is better; unit: PERCENT.

- [Trunk IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Trunk%20IoU>): Higher is better; unit: PERCENT.

- [Terra. IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Terra.%20IoU>): Higher is better; unit: PERCENT.

- [Pole IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Pole%20IoU>): Higher is better; unit: PERCENT.

- [Traf. IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=Traf.%20IoU>): Higher is better; unit: PERCENT.

- [mIoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-synlidar-to-semanticstf-transfer-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Car IoU | Result date | Report paper |
| --- | --- | --- | --- |
| Oracle | 89.4 | Not recorded | 690988953ef7ccd74e5e5e7f |
| UniMix | 65.4 | Not recorded | 690988953ef7ccd74e5e5e7f |
| Light Geometry-Aware Adapter | 49.1 | Not recorded | 690988953ef7ccd74e5e5e7f |
| No Thing, Nothing | 48.4 | Not recorded | 690988953ef7ccd74e5e5e7f |
| DGLSS | 47.9 | Not recorded | 690988953ef7ccd74e5e5e7f |
| DGUIL | 43.3 | Not recorded | 690988953ef7ccd74e5e5e7f |
| PolarMix | 39.2 | Not recorded | 690988953ef7ccd74e5e5e7f |
| LiDARWeather | 39 | Not recorded | 690988953ef7ccd74e5e5e7f |
| PointDR | 37.8 | Not recorded | 690988953ef7ccd74e5e5e7f |
| PCL | 30.9 | Not recorded | 690988953ef7ccd74e5e5e7f |
| Dropout | 28 | Not recorded | 690988953ef7ccd74e5e5e7f |
| Source-only | 27.1 | Not recorded | 690988953ef7ccd74e5e5e7f |
| Perturbation | 27.1 | Not recorded | 690988953ef7ccd74e5e5e7f |
| MMD | 25.5 | Not recorded | 690988953ef7ccd74e5e5e7f |

### Oracle

Car IoU: 89.4. Result ID: 69cbb51047f34ce924b515f3.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

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

### UniMix

Car IoU: 65.4. Result ID: 69cbb51047f34ce924b515fc.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72cd1e209131cea588ed.md>)

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

### Light Geometry-Aware Adapter

Car IoU: 49.1. Result ID: 69cbb51047f34ce924b51600.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

Recorded evaluation configuration: {"mode":"Ours"}. This record does not assert independent reproduction.

### No Thing, Nothing

Car IoU: 48.4. Result ID: 69cbb51047f34ce924b515ff.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa778f1e209131cea73e03.md>)

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

### DGLSS

Car IoU: 47.9. Result ID: 69cbb51047f34ce924b515fb.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

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

### DGUIL

Car IoU: 43.3. Result ID: 69cbb51047f34ce924b515fd.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

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

### PolarMix

Car IoU: 39.2. Result ID: 69cbb51047f34ce924b515f7.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d1c1e209131cea37cf7.md>)

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

### LiDARWeather

Car IoU: 39. Result ID: 69cbb51047f34ce924b515fe.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74211e209131cea5fdb5.md>)

[Implementation](<https://github.com/engineerJPark/LiDARWeather>)

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

### PointDR

Car IoU: 37.8. Result ID: 69cbb51047f34ce924b515fa.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

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

### PCL

Car IoU: 30.9. Result ID: 69cbb51047f34ce924b515f9.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

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

### Dropout

Car IoU: 28. Result ID: 69cbb51047f34ce924b515f5.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

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

### Source-only

Car IoU: 27.1. Result ID: 69cbb51047f34ce924b515f4.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

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

### Perturbation

Car IoU: 27.1. Result ID: 69cbb51047f34ce924b515f6.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.md>)

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

### MMD

Car IoU: 25.5. Result ID: 69cbb51047f34ce924b515f8.

[Reporting paper](<https://www.sota2.com/research/paper/690988953ef7ccd74e5e5e7f.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.
