# 3D Object Detection on Waymo 1% label (val) Source: [3D Object Detection on Waymo 1% label (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:08:11.726Z Evaluation of 3D Object Detection performance on the validation split of the Waymo 1% labeled subset, reporting AP and APH metrics across Level 1 and Level 2 difficulty settings for Vehicle, Pedestrian, and Cyclist 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 1% label (val) | | Metric | Vehicle (L1) AP | | 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 - [Vehicle (L1) AP](): Higher is better; unit: PERCENT. - [Vehicle (L1) APH](): Higher is better; unit: PERCENT. - [Vehicle (L2) AP](): Higher is better; unit: PERCENT. - [Vehicle (L2) APH](): Higher is better; unit: PERCENT. - [Pedestrian (L1) AP](): Higher is better; unit: PERCENT. - [Pedestrian (L1) APH](): Higher is better; unit: PERCENT. - [Pedestrian (L2) AP](): Higher is better; unit: PERCENT. - [Pedestrian (L2) APH](): Higher is better; unit: PERCENT. - [Cyclist (L1) AP](): Higher is better; unit: PERCENT. - [Cyclist (L1) APH](): Higher is better; unit: PERCENT. - [Cyclist (L2) AP](): Higher is better; unit: PERCENT. - [Cyclist (L2) APH](): Higher is better; unit: PERCENT. ## Recorded results | Method | Vehicle (L1) AP | Result date | Report paper | | --- | --- | --- | --- | | PTPM | 61.5 | Not recorded | 68fa7bb51e209131cea8a09f | | Ours | 58.8 | Not recorded | 68fa7bb51e209131cea8a09f | | A-Teacher | 56.5 | Not recorded | 68fa7bb51e209131cea8a09f | | HSSDA | 56.4 | Not recorded | 68fa7bb51e209131cea8a09f | | HSSDA | 54.9 | Not recorded | 68fa7bb51e209131cea8a09f | | DetMatch | 52.2 | Not recorded | 68fa7bb51e209131cea8a09f | | Voxel-RCNN | 49 | Not recorded | 68fa7bb51e209131cea8a09f | | PV-RCNN | 48.5 | Not recorded | 68fa7bb51e209131cea8a09f | ### PTPM Vehicle (L1) AP: 61.5. Result ID: 699cdd975698665ec47e5801. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threshold":"Manual","Base Detector":"PV-RCNN"}. This record does not assert independent reproduction. ### Ours Vehicle (L1) AP: 58.8. Result ID: 699cdd975698665ec47e5804. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threshold":"Auto","Base Detector":"Voxel-RCNN"}. This record does not assert independent reproduction. ### A-Teacher Vehicle (L1) AP: 56.5. Result ID: 699cdd975698665ec47e5800. [Reporting paper]() Recorded evaluation configuration: {"Threshold":"Manual","Base Detector":"PV-RCNN","additional video information":true}. This record does not assert independent reproduction. ### HSSDA Vehicle (L1) AP: 56.4. Result ID: 699cdd975698665ec47e5802. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threshold":"Auto","Base Detector":"PV-RCNN"}. This record does not assert independent reproduction. ### HSSDA Vehicle (L1) AP: 54.9. Result ID: 699cdd975698665ec47e5803. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threshold":"Auto","Base Detector":"Voxel-RCNN"}. This record does not assert independent reproduction. ### DetMatch Vehicle (L1) AP: 52.2. Result ID: 699cdd975698665ec47e57ff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threshold":"Manual","Base Detector":"PV-RCNN"}. This record does not assert independent reproduction. ### Voxel-RCNN Vehicle (L1) AP: 49. Result ID: 699cdd975698665ec47e57fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threshold":"Detector","Base Detector":"Voxel-RCNN"}. This record does not assert independent reproduction. ### PV-RCNN Vehicle (L1) AP: 48.5. Result ID: 699cdd975698665ec47e57fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threshold":"Detector","Base Detector":"PV-RCNN"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.