paper-with-me

3D Object Detection 벤치마크

3D Object Detection on KITTI Cyclists Easy

72개 결과 · ⬇ CSV · JSON

AP

61.22 68.2 75.19 82.17 89.15 2017-11 2026-11 VoxelNet — 61.22 (2017-11-17) VoxelNet — 61.22 (2017-11-17) VoxelNet — 61.22 (2017-11-17) VoxelNet — 61.22 (2017-11-17) VoxelNet — 61.22 (2017-11-17) VoxelNet — 61.22 (2017-11-17) Frustum PointNets — 71.96 (2017-11-22) Frustum PointNets — 71.96 (2017-11-22) Frustum PointNets — 71.96 (2017-11-22) Frustum PointNets — 71.96 (2017-11-22) Frustum PointNets — 71.96 (2017-11-22) Frustum PointNets — 71.96 (2017-11-22) AVOD + Feature Pyramid — 64.0 (2017-12-06) AVOD + Feature Pyramid — 64.0 (2017-12-06) AVOD + Feature Pyramid — 64.0 (2017-12-06) AVOD + Feature Pyramid — 64.0 (2017-12-06) AVOD + Feature Pyramid — 64.0 (2017-12-06) AVOD + Feature Pyramid — 64.0 (2017-12-06) PointRCNN — 73.93 (2018-12-11) PointRCNN — 73.93 (2018-12-11) PointRCNN — 73.93 (2018-12-11) PointRCNN — 73.93 (2018-12-11) PointRCNN — 73.93 (2018-12-11) PointRCNN — 73.93 (2018-12-11) IPOD — 71.4 (2018-12-13) IPOD — 71.4 (2018-12-13) IPOD — 71.4 (2018-12-13) IPOD — 71.4 (2018-12-13) IPOD — 71.4 (2018-12-13) IPOD — 71.4 (2018-12-13) PointPillars — 75.78 (2018-12-14) PointPillars — 75.78 (2018-12-14) PointPillars — 75.78 (2018-12-14) PointPillars — 75.78 (2018-12-14) PointPillars — 75.78 (2018-12-14) PointPillars — 75.78 (2018-12-14) F-ConvNet — 79.58 (2019-03-05) F-ConvNet — 79.58 (2019-03-05) F-ConvNet — 79.58 (2019-03-05) F-ConvNet — 79.58 (2019-03-05) F-ConvNet — 79.58 (2019-03-05) F-ConvNet — 79.58 (2019-03-05) STD — 78.89 (2019-07-22) STD — 78.89 (2019-07-22) STD — 78.89 (2019-07-22) STD — 78.89 (2019-07-22) STD — 78.89 (2019-07-22) STD — 78.89 (2019-07-22) PV-RCNN — 78.6 (2019-12-31) PV-RCNN — 78.6 (2019-12-31) PV-RCNN — 78.6 (2019-12-31) PV-RCNN — 78.6 (2019-12-31) PV-RCNN — 78.6 (2019-12-31) PV-RCNN — 78.6 (2019-12-31) SVGA-Net — 79.22 (2020-06-07) SVGA-Net — 79.22 (2020-06-07) SVGA-Net — 79.22 (2020-06-07) SVGA-Net — 79.22 (2020-06-07) SVGA-Net — 79.22 (2020-06-07) SVGA-Net — 79.22 (2020-06-07) M3DeTR — 83.83 (2021-04-24) M3DeTR — 83.83 (2021-04-24) M3DeTR — 83.83 (2021-04-24) M3DeTR — 83.83 (2021-04-24) M3DeTR — 83.83 (2021-04-24) M3DeTR — 83.83 (2021-04-24) 3D-FCT — 89.15 (2021-10-06) 3D-FCT — 89.15 (2021-10-06) 3D-FCT — 89.15 (2021-10-06) 3D-FCT — 89.15 (2021-10-06) 3D-FCT — 89.15 (2021-10-06) 3D-FCT — 89.15 (2021-10-06) VoxelNet — 61.22 (2017-11-17) Frustum PointNets — 71.96 (2017-11-22) PointRCNN — 73.93 (2018-12-11) PointPillars — 75.78 (2018-12-14) F-ConvNet — 79.58 (2019-03-05) M3DeTR — 83.83 (2021-04-24) 3D-FCT — 89.15 (2021-10-06)
RankModel AP PaperCodeYear
1 3D-FCT 89.15% 3D-FCT: Simultaneous 3D Object Detection and Tracking Using Feature Correlation 2021
2 M3DeTR 83.83% M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers rayguan97/M3DeTR 2021
3 F-ConvNet 79.58% Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection zhixinwang/frustum-convnet · carterprice2/Deep_Learning_project 2019
4 SVGA-Net 79.22% SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds 2020
5 STD 78.89% STD: Sparse-to-Dense 3D Object Detector for Point Cloud 2019
6 PV-RCNN 78.60% PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection open-mmlab/OpenPCDet · jhultman/PV-RCNN · sshaoshuai/PV-RCNN · +9 2019
7 PointPillars 75.78% PointPillars: Fast Encoders for Object Detection from Point Clouds open-mmlab/mmdetection3d · isl-org/Open3D-ML · nvidia-ai-iot/lidar_ai_solution · +15 2018
8 PointRCNN 73.93% PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud isl-org/Open3D-ML · sshaoshuai/PointRCNN · sshaoshuai/Pointnet2.PyTorch · +10 2018
9 Frustum PointNets 71.96% Frustum PointNets for 3D Object Detection from RGB-D Data charlesq34/pointnet · charlesq34/pointnet2 · charlesq34/frustum-pointnets · +65 2017
10 IPOD 71.40% IPOD: Intensive Point-based Object Detector for Point Cloud 2018
11 AVOD + Feature Pyramid 64.0% Joint 3D Proposal Generation and Object Detection from View Aggregation kujason/avod · kujason/ip_basic · asharakeh/kitti_native_evaluation · +1 2017
12 VoxelNet 61.22% VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection qianguih/voxelnet · skyhehe123/voxelnet-pytorch · steph1793/Voxelnet · +41 2017
13 3D-FCT 89.15% 3D-FCT: Simultaneous 3D Object Detection and Tracking Using Feature Correlation 2021
14 M3DeTR 83.83% M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers rayguan97/M3DeTR 2021
15 F-ConvNet 79.58% Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection zhixinwang/frustum-convnet · carterprice2/Deep_Learning_project 2019
16 SVGA-Net 79.22% SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds 2020
17 STD 78.89% STD: Sparse-to-Dense 3D Object Detector for Point Cloud 2019
18 PV-RCNN 78.60% PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection open-mmlab/OpenPCDet · jhultman/PV-RCNN · sshaoshuai/PV-RCNN · +9 2019
19 PointPillars 75.78% PointPillars: Fast Encoders for Object Detection from Point Clouds open-mmlab/mmdetection3d · isl-org/Open3D-ML · nvidia-ai-iot/lidar_ai_solution · +15 2018
20 PointRCNN 73.93% PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud isl-org/Open3D-ML · sshaoshuai/PointRCNN · sshaoshuai/Pointnet2.PyTorch · +10 2018
1–20 / 72 다음 → 페이지당 10 20 50 100