# 3D Object Detection on nuScenes LiDAR Scene Corruptions v1.0 (test)

Source: [3D Object Detection on nuScenes LiDAR Scene Corruptions v1.0 (test)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test>)

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

Data updated: 2026-03-10T10:23:32.764Z

Evaluation of 3D Object Detection performance on the nuScenes LiDAR Scene Corruptions v1.0 test set, reporting metrics (NDS/mAP) across various simulated LiDAR sensor degradations such as Beam Missing, Crosstalk, Fog, and Motion Blur.

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 | 3D Object Detection |
| Dataset (including any stated split) | nuScenes LiDAR Scene Corruptions v1.0 (test) |
| Metric | NDS (Beam Missing) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [NDS (Beam Missing)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test.md?metric=NDS%20(Beam%20Missing)>): Higher is better; unit: PERCENT.

- [mAP (Beam Missing)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test.md?metric=mAP%20(Beam%20Missing)>): Higher is better; unit: PERCENT.

- [NDS (Crosstalk)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test.md?metric=NDS%20(Crosstalk)>): Higher is better; unit: PERCENT.

- [mAP (Crosstalk)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test.md?metric=mAP%20(Crosstalk)>): Higher is better; unit: PERCENT.

- [NDS (Fog)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test.md?metric=NDS%20(Fog)>): Higher is better; unit: PERCENT.

- [mAP (Fog)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test.md?metric=mAP%20(Fog)>): Higher is better; unit: PERCENT.

- [NDS (Incomplete Echo)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test.md?metric=NDS%20(Incomplete%20Echo)>): Higher is better; unit: PERCENT.

- [mAP (Incomplete Echo)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test.md?metric=mAP%20(Incomplete%20Echo)>): Higher is better; unit: PERCENT.

- [NDS (Motion Blur)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test.md?metric=NDS%20(Motion%20Blur)>): Higher is better; unit: PERCENT.

- [mAP (Motion Blur)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test.md?metric=mAP%20(Motion%20Blur)>): Higher is better; unit: PERCENT.

- [NDS (Snow)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test.md?metric=NDS%20(Snow)>): Higher is better; unit: PERCENT.

- [mAP (Snow)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test.md?metric=mAP%20(Snow)>): Higher is better; unit: PERCENT.

- [mRR](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-lidar-scene-corruptions-v1-0-test.md?metric=mRR>): Higher is better; unit: PERCENT.

## Recorded results

| Method | NDS (Beam Missing) | Result date | Report paper |
| --- | --- | --- | --- |
| Multi-Modal Decouple and Recouple Network | 71.3 | Not recorded | 69afa5a72d603e6de3e43d1a |
| BEVFusion | 70.2 | Not recorded | 69afa5a72d603e6de3e43d1a |
| MetaBEV | 70.2 | Not recorded | 69afa5a72d603e6de3e43d1a |
| AD\_BEVFusion | 69.6 | Not recorded | 69afa5a72d603e6de3e43d1a |
| TranFusion | 69.5 | Not recorded | 69afa5a72d603e6de3e43d1a |
| FUTR3D | 69.1 | Not recorded | 69afa5a72d603e6de3e43d1a |
| UVTR | 68.6 | Not recorded | 69afa5a72d603e6de3e43d1a |

### Multi-Modal Decouple and Recouple Network

NDS (Beam Missing): 71.3. Result ID: 69aff1196dbb7075b958fab6.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5a72d603e6de3e43d1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa5a72d603e6de3e43d1a.md>)

Recorded evaluation configuration: {"Severity Level":"Heavy"}. This record does not assert independent reproduction.

### BEVFusion

NDS (Beam Missing): 70.2. Result ID: 69aff1196dbb7075b958fab4.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5a72d603e6de3e43d1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74b01e209131cea63405.md>)

[Implementation](<https://github.com/mit-han-lab/bevfusion>)

Recorded evaluation configuration: {"Severity Level":"Heavy"}. This record does not assert independent reproduction.

### MetaBEV

NDS (Beam Missing): 70.2. Result ID: 69aff1196dbb7075b958fab5.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5a72d603e6de3e43d1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f111e209131cea43a85.md>)

Recorded evaluation configuration: {"Severity Level":"Heavy"}. This record does not assert independent reproduction.

### AD\_BEVFusion

NDS (Beam Missing): 69.6. Result ID: 69aff1196dbb7075b958fab3.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5a72d603e6de3e43d1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6de71e209131cea3ccdb.md>)

[Implementation](<https://github.com/ADLab-AutoDrive/BEVFusion>)

Recorded evaluation configuration: {"Severity Level":"Heavy"}. This record does not assert independent reproduction.

### TranFusion

NDS (Beam Missing): 69.5. Result ID: 69aff1196dbb7075b958fab2.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5a72d603e6de3e43d1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31b48.md>)

Recorded evaluation configuration: {"Severity Level":"Heavy"}. This record does not assert independent reproduction.

### FUTR3D

NDS (Beam Missing): 69.1. Result ID: 69aff1196dbb7075b958fab0.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5a72d603e6de3e43d1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f131e209131cea43b8d.md>)

Recorded evaluation configuration: {"Severity Level":"Heavy"}. This record does not assert independent reproduction.

### UVTR

NDS (Beam Missing): 68.6. Result ID: 69aff1196dbb7075b958fab1.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5a72d603e6de3e43d1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d9f1e209131cea3aedb.md>)

Recorded evaluation configuration: {"Severity Level":"Heavy"}. This record does not assert independent reproduction.

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