Recurrent Slice Networks for 3D Segmentation of Point Clouds

CVPR 2018  ·  Qiangui Huang, Weiyue Wang, Ulrich Neumann ·

Point clouds are an efficient data format for 3D data. However, existing 3D segmentation methods for point clouds either do not model local dependencies \cite{pointnet} or require added computations \cite{kd-net,pointnet2}. This work presents a novel 3D segmentation framework, RSNet\footnote{Codes are released here}, to efficiently model local structures in point clouds. The key component of the RSNet is a lightweight local dependency module. It is a combination of a novel slice pooling layer, Recurrent Neural Network (RNN) layers, and a slice unpooling layer. The slice pooling layer is designed to project features of unordered points onto an ordered sequence of feature vectors so that traditional end-to-end learning algorithms (RNNs) can be applied. The performance of RSNet is validated by comprehensive experiments on the S3DIS\cite{stanford}, ScanNet\cite{scannet}, and ShapeNet \cite{shapenet} datasets. In its simplest form, RSNets surpass all previous state-of-the-art methods on these benchmarks. And comparisons against previous state-of-the-art methods \cite{pointnet, pointnet2} demonstrate the efficiency of RSNets.

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Segmentation S3DIS RSNet Mean IoU 56.5 # 46
mAcc 66.5 # 26
Number of params N/A # 1


No methods listed for this paper. Add relevant methods here