# 3D Object Detection on Waymo Open Dataset Pedestrians (val) Source: [3D Object Detection on Waymo Open Dataset Pedestrians (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:47:56.648Z Evaluation of 3D Object Detection performance on the validation split of the Waymo Open Dataset, focusing specifically on the Pedestrians subset, reporting L1 Average Precision (AP) for 3D and Bird's Eye View (BEV) 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) | Waymo Open Dataset Pedestrians (val) | | Metric | L1 3D AP (IoU=0.5) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 - [L1 3D AP (IoU=0.5)](): Higher is better; unit: PERCENT. - [L1 3D AP (IoU=0.6)](): Higher is better; unit: PERCENT. - [L1 BEV AP (IoU=0.5)](): Higher is better; unit: PERCENT. - [L1 BEV AP (IoU=0.6)](): Higher is better; unit: PERCENT. ## Recorded results | Method | L1 3D AP (IoU=0.5) | Result date | Report paper | | --- | --- | --- | --- | | 3D Auto Labeling | 82.88 | Not recorded | 68fa697c1e209131cea225c5 | | MVF++ | 81.83 | Not recorded | 68fa697c1e209131cea225c5 | | MVF++ | 78.01 | Not recorded | 68fa697c1e209131cea225c5 | | PillarNet | 72.51 | Not recorded | 68fa697c1e209131cea225c5 | | StarNet | 66.8 | Not recorded | 68fa697c1e209131cea225c5 | | PV-RCNN | 65.34 | Not recorded | 68fa697c1e209131cea225c5 | | Multi-view fusion (MVF) | 65.33 | Not recorded | 68fa697c1e209131cea225c5 | | PointPillar | 60.11 | Not recorded | 68fa697c1e209131cea225c5 | ### 3D Auto Labeling L1 3D AP (IoU=0.5): 82.88. Result ID: 698dae438b517eb4332312ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"frames":"all"}. This record does not assert independent reproduction. ### MVF++ L1 3D AP (IoU=0.5): 81.83. Result ID: 698dae438b517eb4332312aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"frames":"5","TTA":true}. This record does not assert independent reproduction. ### MVF++ L1 3D AP (IoU=0.5): 78.01. Result ID: 698dae438b517eb4332312a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"frames":"1"}. This record does not assert independent reproduction. ### PillarNet L1 3D AP (IoU=0.5): 72.51. Result ID: 698dae438b517eb4332312a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"frames":"1"}. This record does not assert independent reproduction. ### StarNet L1 3D AP (IoU=0.5): 66.8. Result ID: 698dae438b517eb4332312a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"frames":"1"}. This record does not assert independent reproduction. ### PV-RCNN L1 3D AP (IoU=0.5): 65.34. Result ID: 698dae438b517eb4332312a8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"frames":"1"}. This record does not assert independent reproduction. ### Multi-view fusion (MVF) L1 3D AP (IoU=0.5): 65.33. Result ID: 698dae438b517eb4332312a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"frames":"1"}. This record does not assert independent reproduction. ### PointPillar L1 3D AP (IoU=0.5): 60.11. Result ID: 698dae438b517eb4332312a5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"frames":"1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.