# 3D Object Detection on nuScenes Dynamic Objects (val)

Source: [3D Object Detection on nuScenes Dynamic Objects (val)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-dynamic-objects-val>)

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

Data updated: 2026-02-26T05:53:08.661Z

Evaluation of 3D Object Detection performance on the nuScenes Dynamic Objects validation split, reporting core metrics like NDS and mAP.

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 Dynamic Objects (val) |
| Metric | NDS |
| 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

- [NDS](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-dynamic-objects-val.md?metric=NDS>): Higher is better; unit: PERCENT.

- [mAP](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-dynamic-objects-val.md?metric=mAP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | NDS | Result date | Report paper |
| --- | --- | --- | --- |
| CMT+AsyncBEV | 43.4 | Not recorded | 69705d9ae25ad2fa9d1ed229 |
| Fan et al. | 37.9 | Not recorded | 69705d9ae25ad2fa9d1ed229 |
| UniBEV+AsyncBEV | 37.8 | Not recorded | 69705d9ae25ad2fa9d1ed229 |

### CMT+AsyncBEV

NDS: 43.4. Result ID: 6997a8ef5698665ec4ff1131.

[Reporting paper](<https://www.sota2.com/research/paper/69705d9ae25ad2fa9d1ed229.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69705d9ae25ad2fa9d1ed229.md>)

Recorded evaluation configuration: {"LiDAR Time Offset":"0.5s"}. This record does not assert independent reproduction.

### Fan et al.

NDS: 37.9. Result ID: 6997a8ef5698665ec4ff1130.

[Reporting paper](<https://www.sota2.com/research/paper/69705d9ae25ad2fa9d1ed229.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa792c1e209131cea7c678.md>)

Recorded evaluation configuration: {"LiDAR Time Offset":"0.5s"}. This record does not assert independent reproduction.

### UniBEV+AsyncBEV

NDS: 37.8. Result ID: 6997a8ef5698665ec4ff1132.

[Reporting paper](<https://www.sota2.com/research/paper/69705d9ae25ad2fa9d1ed229.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69705d9ae25ad2fa9d1ed229.md>)

Recorded evaluation configuration: {"LiDAR Time Offset":"0.5s"}. This record does not assert independent reproduction.

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