# 3D Object Detection on Waymo Open Dataset Level 2 (test) Source: [3D Object Detection on Waymo Open Dataset Level 2 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:08:12.650Z Evaluation of 3D Object Detection performance on the test split of the Waymo Open Dataset, specifically using the Level 2 difficulty configuration, reporting mAP and mAPH for Vehicle and Pedestrian classes. 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 Level 2 (test) | | Metric | Vehicle mAP | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 - [Vehicle mAP](): Higher is better; unit: PERCENT. - [Vehicle mAPH](): Higher is better; unit: PERCENT. - [Pedestrian mAP](): Higher is better; unit: PERCENT. - [Pedestrian mAPH](): Higher is better; unit: PERCENT. ## Recorded results | Method | Vehicle mAP | Result date | Report paper | | --- | --- | --- | --- | | CenterPoint | 72.2 | Not recorded | 68fa6af91e209131cea2b72c | | RCD | 65.1 | Not recorded | 68fa6af91e209131cea2b72c | | PPBA | 59.6 | Not recorded | 68fa6af91e209131cea2b72c | | PointPillars | 55.6 | Not recorded | 68fa6af91e209131cea2b72c | | StarNet | 54.9 | Not recorded | 68fa6af91e209131cea2b72c | ### CenterPoint Vehicle mAP: 72.2. Result ID: 698e487effc3901de09c4d35. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Difficulty":"Level 2"}. This record does not assert independent reproduction. ### RCD Vehicle mAP: 65.1. Result ID: 698e487effc3901de09c4d34. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Difficulty":"Level 2"}. This record does not assert independent reproduction. ### PPBA Vehicle mAP: 59.6. Result ID: 698e487effc3901de09c4d33. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Difficulty":"Level 2"}. This record does not assert independent reproduction. ### PointPillars Vehicle mAP: 55.6. Result ID: 698e487effc3901de09c4d32. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Difficulty":"Level 2"}. This record does not assert independent reproduction. ### StarNet Vehicle mAP: 54.9. Result ID: 698e487effc3901de09c4d31. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Difficulty":"Level 2"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.