3D Object Detection on Waymo Open Dataset 1.2 (val)
72.5Vehicle mAP H L2PTv3
Evaluation Results
| Method | Links | ||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| PTv3Number of input frames=32023.12 | 72.5 | — | — | 73 | — | — | 78 | 75 | — | — | 72.3 | 71.4 | — | 73 | — | — | — | — | |
| PTv3Number of input frames=22023.12 | 72.1 | — | — | 72.5 | — | — | 77.6 | 74.5 | — | — | 71 | 70.1 | — | 72.2 | — | — | — | — | |
| PillarNetNumber of input frames=22023.12 | 71.6 | — | — | 71.6 | — | — | 74.5 | 71.4 | — | — | 68.3 | 67.5 | — | 70.2 | — | — | — | — | |
| CenterPoint++Number of input frames=32023.12 | 71.4 | — | — | 71.8 | — | — | 73.5 | 70.8 | — | — | 73.7 | 72.8 | — | 71.6 | — | — | — | — | |
| FlatFormerNumber of input frames=32023.12 | 71 | — | — | 71.4 | — | — | 74.5 | 71.3 | — | — | 74.7 | 73.7 | — | 72 | — | — | — | — | |
| PTv3Number of input frames=12023.12 | 70.8 | — | — | 71.2 | — | — | 76.3 | 70.4 | — | — | 71.5 | 70.4 | — | 70.5 | — | — | — | — | |
| PillarNet-34Detector Category=Dense, Input Frames=Single-frame2022.12 | 70.5 | 79.1 | 78.6 | 70.9 | 80.6 | 74 | 72.3 | 66.2 | 72.3 | 71.2 | 69.7 | 68.7 | 71 | 68.5 | — | — | — | — | |
| ConQueRDetector Category=Sparse, Backbone=2x wider ResNet, BEV feature map=1/4 downscaled, Input Frames=Single-frame2022.12 | 70.5 | 78.4 | 77.9 | 71 | 80.9 | 75.2 | 73.7 | 68.1 | 77.3 | 76.1 | 74.5 | 73.3 | 73.1 | 70.6 | — | — | — | — | |
| ConQueRDetector Category=Sparse, Backbone=2x wider ResNet, BEV feature map=1/4 downscaled, NMS=conducted on pedestrians and cyclists, Input Frames=Single-frame2022.12 | 70.5 | 78.4 | 77.9 | 71 | 82.4 | 76.6 | 75.8 | 70.1 | 77.5 | 76.4 | 75.2 | 74.1 | 74 | 71.6 | — | — | — | — | |
| FlatFormerNumber of input frames=22023.12 | 70.3 | — | — | 70.8 | — | — | 73.8 | 70.5 | — | — | 73.6 | 72.6 | — | 71.2 | — | — | — | — | |
| PV-RCNN++Detector Category=Dense, Input Frames=Single-frame2022.12 | 70.2 | 79.3 | 78.8 | 70.6 | 81.3 | 76.3 | 73.2 | 68 | 73.7 | 72.7 | 71.2 | 70.2 | 71.7 | 69.5 | — | — | — | — | |
| PillarNetNumber of input frames=12023.12 | 69.9 | — | — | 70.4 | — | — | 71.6 | 64.9 | — | — | 67.8 | 66.7 | — | 67.2 | — | — | — | — | |
| CenterFormerDetector Category=Dense, Input Frames=Single-frame2022.12 | 69.7 | 75.2 | 74.7 | 70.2 | 78.6 | 73 | 73.6 | 68.3 | 72.3 | 71.3 | 69.8 | 68.8 | 71.2 | 69 | — | — | — | — | |
| AFDetV2Detector Category=Dense, Input Frames=Single-frame2022.12 | 69.2 | 77.6 | 77.1 | 69.7 | 80.2 | 74.6 | 72.2 | 67 | 73.7 | 72.7 | 71 | 70.1 | 71 | 68.8 | — | — | — | — | |
| SWFormerDetector Category=Dense, Input Frames=Single-frame2022.12 | 68.8 | 77.8 | 77.3 | 69.2 | 80.9 | 72.7 | 72.5 | 64.9 | — | — | — | — | — | — | — | — | — | — | |
| FlatFormerNumber of input frames=12023.12 | 68.6 | — | — | 69 | — | — | 71.5 | 65.3 | — | — | 68.6 | 67.5 | — | 67.2 | — | — | — | — | |
| PV-RCNNDataset Version=1.22019.12 | 68.41 | 77.51 | 76.89 | 68.98 | 75.01 | 65.65 | 66.04 | 57.61 | 67.81 | 66.35 | 65.39 | 63.98 | — | — | — | — | — | — | |
| PV-RCNNDetector Category=Dense, Input Frames=Single-frame2022.12 | 68.4 | 77.5 | 76.9 | 69 | 75 | 65.6 | 66 | 57.6 | 67.8 | 66.4 | 65.4 | 64 | 66.8 | 63.3 | — | — | — | — | |
| ConQueRDetector Category=Sparse, Input Frames=Single-frame2022.12 | 68.2 | 76.1 | 75.6 | 68.7 | 79 | 72.3 | 70.9 | 64.7 | 73.9 | 72.5 | 71.4 | 70.1 | 70.3 | 67.7 | — | — | — | — | |
| SST_TSDetector Category=Dense, Model Stages=Two-stage, Input Frames=Single-frame2022.12 | 67.6 | 76.2 | 75.8 | 68 | 81.4 | 74.1 | 72.8 | 65.9 | — | — | — | — | — | — | — | — | — | — | |
| CenterPointDetector Category=Dense, Input Frames=Single-frame2022.12 | 67.4 | — | — | — | — | — | — | 65.6 | — | — | — | 68.6 | — | 67.9 | — | — | — | — | |
| Voxel-DETRDetector Category=Sparse, Input Frames=Single-frame2022.12 | 67.2 | 75.4 | 74.9 | 67.8 | 77.6 | 70.5 | 69.7 | 63.1 | 71.7 | 70.5 | 69 | 67.9 | 68.8 | 66.1 | — | — | — | — | |
| CenterPointNumber of input frames=22023.12 | 67.2 | — | — | 67.7 | — | — | 71 | 67.5 | — | — | 71.5 | 70.5 | — | 68.4 | — | — | — | — | |
| CenterPointNumber of input frames=12023.12 | 66.2 | — | — | 66.7 | — | — | 68.3 | 62.6 | — | — | 68.7 | 67.6 | — | 65.5 | — | — | — | — | |
| SST-CenterNumber of input frames=12023.12 | 66.2 | — | — | 66.6 | — | — | 72.4 | 65 | — | — | 68.9 | 67.6 | — | 66.3 | — | — | — | — | |
| SSTNumber of input frames=32023.12 | 66.1 | — | — | 66.5 | — | — | 76.2 | 72.3 | — | — | 73.6 | 72.8 | — | 70.4 | — | — | — | — | |
| VoxSetNumber of input frames=12023.12 | 65.6 | — | — | 66 | — | — | 72.5 | 65.4 | — | — | 69 | 67.7 | — | 66.2 | — | — | — | — | |
| TransFusion-LDetector Category=Sparse, Input Frames=Single-frame2022.12 | 65.1 | — | — | — | — | — | — | 63.7 | — | — | — | 65.9 | — | 64.9 | — | — | — | — | |
| SSTNumber of input frames=12023.12 | 64.4 | — | — | 64.8 | — | — | 71.7 | 63 | — | — | 68 | 66.9 | — | 64.8 | — | — | — | — | |
| BoxeR-3DDetector Category=Sparse, Input Frames=Single-frame2022.12 | 63.7 | 70.4 | 70 | 63.9 | 64.7 | 53.5 | 61.5 | 53.7 | 50.2 | 48.9 | — | — | — | — | — | — | — | — | |
| SECONDReference=Sensors 2018, Implementation=re-implemented2019.12 | 63.33 | 72.27 | 71.69 | 63.85 | 68.7 | 58.18 | 60.72 | 51.31 | 60.62 | 59.28 | 58.34 | 57.05 | — | — | — | — | — | — | |
| PointPillarsNumber of input frames=12023.12 | 63.1 | — | — | 63.6 | — | — | 62.8 | 50.3 | — | — | 61.9 | 59.9 | — | 57.8 | — | — | — | — | |
| BA-DetTemporal Information=true2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1,660 | 1,645 | 409.3 | 405.1 | |
| BA-DetTemporal Information=true2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1,557 | 1,544 | |
| BEVFormerTemporal Information=true2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 770 | — | 308 | |
| BEVFormerTemporal Information=true2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 690 | |
| CaDDNTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 503 | 499 | 175.4 | 173.1 | |
| CaDDNTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 449 | 445 | |
| DCDTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1,257 | 1,250 | 334.4 | 332.4 | |
| DCDTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1,178 | 1,172 | |
| DEVIANTTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 269 | 267 | 109.8 | 108.9 | |
| DEVIANTTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 252 | 250 | |
| DID-M3DTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 206.6 | 204.7 | |
| DID-M3DTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 19.37 | 19.19 | |
| GUPNetTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 228 | 227 | 100.2 | 99.4 | |
| GUPNetTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 214 | 212 | |
| M3D-RPNTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 35 | 34 | 37.9 | 36.3 | |
| M3D-RPNTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 33 | 33 | |
| MonoFlexTemporal Information=false, Baseline=true2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1,170 | 1,164 | 322.6 | 320.6 | |
| MonoFlexTemporal Information=false, Baseline=true2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1,096 | 1,090 | |
| MonoJSGTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 97 | 95 | 56.5 | 54.7 | |
| MonoJSGTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 91 | 89 | |
| MVFReference=CORL 2019, Dataset Version=1.02019.12 | — | 62.93 | — | — | 65.33 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PatchNetTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 39 | 37 | 29.2 | 27.4 | |
| PatchNetTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 38 | 36 | |
| PCTTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 89 | 88 | 42 | 41.5 | |
| PCTTemporal Information=false2023.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 66 | 66 | |
| PointPillarReference=CVPR 2019, Dataset Version=1.02019.12 | — | 56.62 | — | — | 59.25 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| StarNetReference=NeurIPSw 2019, Dataset Version=1.02019.12 | — | 53.7 | — | — | 66.8 | — | — | — | — | — | — | — | — | — | — | — | — | — |