ECCV2018中对于点云的处理提出的很多新方法，相关文章列表如下：
- Fully-Convolutional Point Networks for Large-Scale Point Clouds
- Multiresolution Tree Networks for 3D Point Cloud Processing
- 3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation
- Learning and Matching Multi-View Descriptors for Registration of Point Clouds
- 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
- Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search
- Efficient Dense Point Cloud Object Reconstruction using Deformation Vector Fields