# Bird's Eye View (BEV) Object Detection on KITTI official (new evaluation metric) (test) Source: [Bird's Eye View (BEV) Object Detection on KITTI official (new evaluation metric) (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:36:43.823Z Evaluation of Bird's Eye View (BEV) Object Detection performance on the KITTI official test set, specifically utilizing a new evaluation metric configuration, reporting BEV Detection Average Precision (AP) across Easy, Moderate, and Hard difficulty levels. 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 | Bird's Eye View (BEV) Object Detection | | Dataset (including any stated split) | KITTI official leaderboard (new evaluation metric) (test) | | Metric | BEV Detection AP (Easy) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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 - [BEV Detection AP (Easy)](): Higher is better; unit: PERCENT. - [BEV Detection AP (Moderate)](): Higher is better; unit: PERCENT. - [BEV Detection AP (Hard)](): Higher is better; unit: PERCENT. ## Recorded results | Method | BEV Detection AP (Easy) | Result date | Report paper | | --- | --- | --- | --- | | MV3D (LiDAR) | 86.49 | Not recorded | 68fa67521e209131cea15711 | | DSGN | 82.9 | Not recorded | 68fa67521e209131cea15711 | | PL++: P-RCNN\* | 78.31 | Not recorded | 68fa67521e209131cea15711 | | PL: AVOD\* | 67.3 | Not recorded | 68fa67521e209131cea15711 | | Stereo R-CNN\* | 61.92 | Not recorded | 68fa67521e209131cea15711 | | AM3D | 25.03 | Not recorded | 68fa67521e209131cea15711 | | M3D-RPN | 21.02 | Not recorded | 68fa67521e209131cea15711 | | MonoGRNet | 18.19 | Not recorded | 68fa67521e209131cea15711 | | OFT-Net | 7.16 | Not recorded | 68fa67521e209131cea15711 | ### MV3D (LiDAR) BEV Detection AP (Easy): 86.49. Result ID: 698d2ab78b517eb4331f7f21. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modality":"LiDAR"}. This record does not assert independent reproduction. ### DSGN BEV Detection AP (Easy): 82.9. Result ID: 698d2ab78b517eb4331f7f29. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"Stereo"}. This record does not assert independent reproduction. ### PL++: P-RCNN\* BEV Detection AP (Easy): 78.31. Result ID: 698d2ab78b517eb4331f7f28. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"Stereo","Pre-training":"Scene Flow"}. This record does not assert independent reproduction. ### PL: AVOD\* BEV Detection AP (Easy): 67.3. Result ID: 698d2ab78b517eb4331f7f27. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"Stereo","Pre-training":"Scene Flow"}. This record does not assert independent reproduction. ### Stereo R-CNN\* BEV Detection AP (Easy): 61.92. Result ID: 698d2ab78b517eb4331f7f26. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"Stereo","Pre-training":"ImageNet"}. This record does not assert independent reproduction. ### AM3D BEV Detection AP (Easy): 25.03. Result ID: 698d2ab78b517eb4331f7f25. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modality":"Mono"}. This record does not assert independent reproduction. ### M3D-RPN BEV Detection AP (Easy): 21.02. Result ID: 698d2ab78b517eb4331f7f24. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"Mono"}. This record does not assert independent reproduction. ### MonoGRNet BEV Detection AP (Easy): 18.19. Result ID: 698d2ab78b517eb4331f7f23. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Modality":"Mono"}. This record does not assert independent reproduction. ### OFT-Net BEV Detection AP (Easy): 7.16. Result ID: 698d2ab78b517eb4331f7f22. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modality":"Mono"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.