# Multi-task Autonomous Driving Perception on nuScenes-lidarseg (test)

Source: [Multi-task Autonomous Driving Perception on nuScenes-lidarseg (test)](<https://www.sota2.com/research/sota/multi-task-autonomous-driving-perception-on-nuscenes-lidarseg-test>)

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

Data updated: 2026-06-04T07:43:47.085Z

Evaluation of multi-task perception capabilities, including metrics like Mean Absolute Error for Depth Estimation (MAE\_DE) and various Intersection over Union scores (IoU), using the test split of the nuScenes LiDAR segmentation subset.

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 | Multi-task Autonomous Driving Perception |
| Dataset (including any stated split) | nuScenes-lidarseg (test) |
| Metric | IoU (BEVP) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [IoU (BEVP)](<https://www.sota2.com/research/sota/multi-task-autonomous-driving-perception-on-nuscenes-lidarseg-test.md?metric=IoU%20(BEVP)>): Higher is better; unit: PERCENT.

- [MAE (Depth Estimation)](<https://www.sota2.com/research/sota/multi-task-autonomous-driving-perception-on-nuscenes-lidarseg-test.md?metric=MAE%20(Depth%20Estimation)>): Lower is better; unit: SCALAR.

- [IoU (Small Scale)](<https://www.sota2.com/research/sota/multi-task-autonomous-driving-perception-on-nuscenes-lidarseg-test.md?metric=IoU%20(Small%20Scale)>): Higher is better; unit: PERCENT.

- [IoU (Large Scale)](<https://www.sota2.com/research/sota/multi-task-autonomous-driving-perception-on-nuscenes-lidarseg-test.md?metric=IoU%20(Large%20Scale)>): Higher is better; unit: PERCENT.

- [TM](<https://www.sota2.com/research/sota/multi-task-autonomous-driving-perception-on-nuscenes-lidarseg-test.md?metric=TM>): Higher is better; unit: SCALAR.

- [MV](<https://www.sota2.com/research/sota/multi-task-autonomous-driving-perception-on-nuscenes-lidarseg-test.md?metric=MV>): Lower is better; unit: PERCENT.

## Recorded results

| Method | IoU (BEVP) | Result date | Report paper |
| --- | --- | --- | --- |
| 15L+MGN | 83.3 | Not recorded | 6a210684c10484bac23f00e1 |
| 15L | 82.4 | Not recorded | 6a210684c10484bac23f00e1 |
| 1L | 80.4 | Not recorded | 6a210684c10484bac23f00e1 |
| Chen et al. | 78.8 | Not recorded | 6a210684c10484bac23f00e1 |

### 15L+MGN

IoU (BEVP): 83.3. Result ID: 6a212cb0fbc373592c1c6cd6.

[Reporting paper](<https://www.sota2.com/research/paper/6a210684c10484bac23f00e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a210684c10484bac23f00e1.md>)

Recorded evaluation configuration: {"LiDAR Layers":"15L","Multi-Gate Network":"true","RGB-only encoder":"true"}. This record does not assert independent reproduction.

### 15L

IoU (BEVP): 82.4. Result ID: 6a212cb0fbc373592c1c6cd5.

[Reporting paper](<https://www.sota2.com/research/paper/6a210684c10484bac23f00e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a210684c10484bac23f00e1.md>)

Recorded evaluation configuration: {"LiDAR Layers":"15L","RGB-only encoder":"true"}. This record does not assert independent reproduction.

### 1L

IoU (BEVP): 80.4. Result ID: 6a212cb0fbc373592c1c6cd4.

[Reporting paper](<https://www.sota2.com/research/paper/6a210684c10484bac23f00e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a210684c10484bac23f00e1.md>)

Recorded evaluation configuration: {"LiDAR Layers":"1L","RGB-only encoder":"true"}. This record does not assert independent reproduction.

### Chen et al.

IoU (BEVP): 78.8. Result ID: 6a212cb0fbc373592c1c6cd1.

[Reporting paper](<https://www.sota2.com/research/paper/6a210684c10484bac23f00e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68821e209131cea1c8b3.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.
