Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection

Benchmark Model Rank Results
3d-object-detection-on-kitti-pedestrians-easyF-ConvNet#1AP: 52.37%
3d-object-detection-on-kitti-pedestrians-hardF-ConvNet#1AP: 41.49%
3d-object-detection-on-kitti-pedestrians-moderateF-ConvNet#1AP: 43.38%
3d-object-detection-on-kitti-cyclists-easyF-ConvNet#3AP: 79.58%
3d-object-detection-on-kitti-cyclists-moderateF-ConvNet#3AP: 64.68%
3d-object-detection-on-kitti-cyclists-hardF-ConvNets#5AP: 57.03%
3d-object-detection-on-kitti-cars-easyF-ConvNet#9AP: 85.88%
3d-object-detection-on-kitti-cars-hardF-ConvNet#10AP: 68.08%