# LiDAR Semantic Segmentation on nuScenes (unseen scenes)

Source: [LiDAR Semantic Segmentation on nuScenes (unseen scenes)](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-nuscenes-unseen-scenes>)

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

Data updated: 2026-04-15T08:24:50.101Z

Evaluation of LiDAR-based Semantic Segmentation performance on the 'unseen scenes' subset of the nuScenes dataset.

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) | nuScenes (unseen scenes) |
| Metric | mIoU |
| Unit | PERCENT |
| 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

- [mIoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-nuscenes-unseen-scenes.md?metric=mIoU>): Higher is better; unit: PERCENT.

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

- [Bicycle IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-nuscenes-unseen-scenes.md?metric=Bicycle%20IoU>): Higher is better; unit: PERCENT.

- [Motorcycle IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-nuscenes-unseen-scenes.md?metric=Motorcycle%20IoU>): Higher is better; unit: PERCENT.

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

- [Pedestrian IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-nuscenes-unseen-scenes.md?metric=Pedestrian%20IoU>): Higher is better; unit: PERCENT.

- [Terrain IoU](<https://www.sota2.com/research/sota/lidar-semantic-segmentation-on-nuscenes-unseen-scenes.md?metric=Terrain%20IoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| HyperLiDAR-full | 67.3 | Not recorded | 69df1b727d0172140ec7b7ce |
| SALUDA | 65.2 | Not recorded | 69df1b727d0172140ec7b7ce |
| HyperLiDAR | 61.6 | Not recorded | 69df1b727d0172140ec7b7ce |
| CENET | 54.5 | Not recorded | 69df1b727d0172140ec7b7ce |

### HyperLiDAR-full

mIoU: 67.3. Result ID: 69df4b4447f34ce924c803f3.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b727d0172140ec7b7ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1b727d0172140ec7b7ce.md>)

Recorded evaluation configuration: {"Buffer Selection":"Full update"}. This record does not assert independent reproduction.

### SALUDA

mIoU: 65.2. Result ID: 69df4b4447f34ce924c803f1.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b727d0172140ec7b7ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73e31e209131cea5eb14.md>)

Recorded evaluation configuration: {"Model":"SALUDA"}. This record does not assert independent reproduction.

### HyperLiDAR

mIoU: 61.6. Result ID: 69df4b4447f34ce924c803f2.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b727d0172140ec7b7ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1b727d0172140ec7b7ce.md>)

Recorded evaluation configuration: {"Buffer Selection":"Active (5%)"}. This record does not assert independent reproduction.

### CENET

mIoU: 54.5. Result ID: 69df4b4447f34ce924c803f0.

[Reporting paper](<https://www.sota2.com/research/paper/69df1b727d0172140ec7b7ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d1e1e209131cea37e55.md>)

[Implementation](<https://github.com/huixiancheng/CENet>)

Recorded evaluation configuration: {"Model":"CENET"}. This record does not assert independent reproduction.

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