Deformable Filter Convolution for Point Cloud Reasoning

30 Jul 2019  ·  Yuwen Xiong, Mengye Ren, Renjie Liao, Kelvin Wong, Raquel Urtasun ·

Point clouds are the native output of many real-world 3D sensors. To borrow the success of 2D convolutional network architectures, a majority of popular 3D perception models voxelize the points, which can result in a loss of local geometric details that cannot be recovered. In this paper, we propose a novel learnable convolution layer for processing 3D point cloud data directly. Instead of discretizing points into fixed voxels, we deform our learnable 3D filters to match with the point cloud shape. We propose to combine voxelized backbone networks with our deformable filter layer at 1) the network input stream and 2) the output prediction layers to enhance point level reasoning. We obtain state-of-the-art results on LiDAR semantic segmentation and producing a significant gain in performance on LiDAR object detection.

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.