# 3D Object Detection on nuScenes (val) (Weather and Motion Robustness) Source: [3D Object Detection on nuScenes (val) (Weather and Motion Robustness)]() Collection index: [llms.txt]() Data updated: 2026-03-10T10:23:32.716Z Evaluation of 3D Object Detection performance on the standard nuScenes validation set, reporting metrics specifically across Fog, Snow, and Motion Blur conditions, alongside baseline Clean metrics. 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 (val) | | Metric | Clean NDS | | 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 - [Clean NDS](): Higher is better; unit: PERCENT. - [Clean mAP](): Higher is better; unit: PERCENT. - [Fog NDS](): Higher is better; unit: PERCENT. - [Fog mAP](): Higher is better; unit: PERCENT. - [Snow NDS](): Higher is better; unit: PERCENT. - [Snow mAP](): Higher is better; unit: PERCENT. - [MotionBlur NDS](): Higher is better; unit: PERCENT. - [MotionBlur mAP](): Higher is better; unit: PERCENT. - [mRR](): Higher is better; unit: PERCENT. ## Recorded results | Method | Clean NDS | Result date | Report paper | | --- | --- | --- | --- | | Multi-Modal Decouple and Recouple Network | 72 | Not recorded | 69afa5a72d603e6de3e43d1a | | BEVFusion | 71.4 | Not recorded | 69afa5a72d603e6de3e43d1a | | MetaBEV | 71.3 | Not recorded | 69afa5a72d603e6de3e43d1a | | TransFusion | 71.2 | Not recorded | 69afa5a72d603e6de3e43d1a | | AD\_BEVFusion | 71 | Not recorded | 69afa5a72d603e6de3e43d1a | | FUTR3D | 70.9 | Not recorded | 69afa5a72d603e6de3e43d1a | | UVTR | 70.2 | Not recorded | 69afa5a72d603e6de3e43d1a | ### Multi-Modal Decouple and Recouple Network Clean NDS: 72. Result ID: 69aff1196dbb7075b958fa5a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BEVFusion Clean NDS: 71.4. Result ID: 69aff1196dbb7075b958fa58. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MetaBEV Clean NDS: 71.3. Result ID: 69aff1196dbb7075b958fa59. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TransFusion Clean NDS: 71.2. Result ID: 69aff1196dbb7075b958fa56. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AD\_BEVFusion Clean NDS: 71. Result ID: 69aff1196dbb7075b958fa57. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FUTR3D Clean NDS: 70.9. Result ID: 69aff1196dbb7075b958fa54. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UVTR Clean NDS: 70.2. Result ID: 69aff1196dbb7075b958fa55. [Reporting paper]() [Method origin paper]() 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.