# 3D Object Detection on SI3D-DI Moderate (test) Source: [3D Object Detection on SI3D-DI Moderate (test)]() Collection index: [llms.txt]() Data updated: 2026-06-09T10:24:18.159Z Evaluation of 3D Object Detection performance on the test split of the SI3D-DI dataset, reporting category-specific Average Precision metrics for Bird's Eye View (BEV) and 3D space. 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) | SI3D-DI Moderate (test) | | Metric | AP BEV (Vehicle) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [AP BEV (Vehicle)](): Higher is better; unit: PERCENT. - [AP 3D (Vehicle)](): Higher is better; unit: PERCENT. - [AP BEV (Art Target)](): Higher is better; unit: PERCENT. - [AP 3D (Art Target)](): Higher is better; unit: PERCENT. - [AP BEV (Cam Target)](): Higher is better; unit: PERCENT. - [AP 3D (Cam Target)](): Higher is better; unit: PERCENT. - [AP BEV (Canopy)](): Higher is better; unit: PERCENT. - [AP 3D (Canopy)](): Higher is better; unit: PERCENT. - [mAP BEV](): Higher is better; unit: PERCENT. - [mAP 3D](): Higher is better; unit: PERCENT. ## Recorded results | Method | AP BEV (Vehicle) | Result date | Report paper | | --- | --- | --- | --- | | CAMF-Det | 72.65 | Not recorded | 6a279e5490966ade919bf9b9 | | TG-ADet | 72.43 | Not recorded | 6a279e5490966ade919bf9b9 | | VoxelNext | 72.26 | Not recorded | 6a279e5490966ade919bf9b9 | | SAFDNet | 68.5 | Not recorded | 6a279e5490966ade919bf9b9 | | Voxelmamba | 63.54 | Not recorded | 6a279e5490966ade919bf9b9 | | SSLFusion | 62.45 | Not recorded | 6a279e5490966ade919bf9b9 | | IS-Fusion | 62.19 | Not recorded | 6a279e5490966ade919bf9b9 | | HEDNet | 60.68 | Not recorded | 6a279e5490966ade919bf9b9 | | AutoAlignv2 | 59.08 | Not recorded | 6a279e5490966ade919bf9b9 | | BEVFusion | 58.67 | Not recorded | 6a279e5490966ade919bf9b9 | | TransFusion-L | 58.66 | Not recorded | 6a279e5490966ade919bf9b9 | | BEVDilation | 35.99 | Not recorded | 6a279e5490966ade919bf9b9 | ### CAMF-Det AP BEV (Vehicle): 72.65. Result ID: 6a27e9cefbc373592c2555fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modal":"L+C","Reference":"Ours"}. This record does not assert independent reproduction. ### TG-ADet AP BEV (Vehicle): 72.43. Result ID: 6a27e9cefbc373592c2555f8. [Reporting paper]() Recorded evaluation configuration: {"Modal":"L","Reference":"TGRS 2025"}. This record does not assert independent reproduction. ### VoxelNext AP BEV (Vehicle): 72.26. Result ID: 6a27e9cefbc373592c2555f5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modal":"L","Reference":"CVPR 2023"}. This record does not assert independent reproduction. ### SAFDNet AP BEV (Vehicle): 68.5. Result ID: 6a27e9cefbc373592c2555f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modal":"L","Reference":"CVPR 2024"}. This record does not assert independent reproduction. ### Voxelmamba AP BEV (Vehicle): 63.54. Result ID: 6a27e9cefbc373592c2555f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modal":"L","Reference":"NeurIPS 2024"}. This record does not assert independent reproduction. ### SSLFusion AP BEV (Vehicle): 62.45. Result ID: 6a27e9cefbc373592c2555fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modal":"L+C","Reference":"AAAI 2025"}. This record does not assert independent reproduction. ### IS-Fusion AP BEV (Vehicle): 62.19. Result ID: 6a27e9cefbc373592c2555fb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modal":"L+C","Reference":"CVPR 2024"}. This record does not assert independent reproduction. ### HEDNet AP BEV (Vehicle): 60.68. Result ID: 6a27e9cefbc373592c2555f4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modal":"L","Reference":"NeurIPS 2023"}. This record does not assert independent reproduction. ### AutoAlignv2 AP BEV (Vehicle): 59.08. Result ID: 6a27e9cefbc373592c2555f9. [Reporting paper]() Recorded evaluation configuration: {"Modal":"L+C","Reference":"ECCV 2022"}. This record does not assert independent reproduction. ### BEVFusion AP BEV (Vehicle): 58.67. Result ID: 6a27e9cefbc373592c2555fa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modal":"L+C","Reference":"ICRA 2023"}. This record does not assert independent reproduction. ### TransFusion-L AP BEV (Vehicle): 58.66. Result ID: 6a27e9cefbc373592c2555f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modal":"L","Reference":"CVPR 2022"}. This record does not assert independent reproduction. ### BEVDilation AP BEV (Vehicle): 35.99. Result ID: 6a27e9cefbc373592c2555fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modal":"L+C","Reference":"AAAI 2026"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.