论文笔记(二)：基于深度学习的数字几何处理与分析技术研究进展

针对网格的处理
1.匹配映射
      1).Learning shape correspondence with anisotropic convolutional neural networks-----2016
      2).Learning class-specific descriptors shapes using localized spectral convolutional networks-----2015
      3).Geometric deep learning on graphs and manifolds using mixture model CNNs-----2017
      4).Jointly learning shape descriptors and their correspondence via deep triplet-----2018
      5).Learning 3D keypoint descriptors for non-rigid shape matching----2018
      6).Deep functional maps:Structured prediction for dense shape correspondence-----2017
2.模型分割
      1).3D mesh labeling via deep convolutional neural networks—2015
      2).Unsupervised 3D shape segmentation and co-segmentation via deep learning–2016
      3).3D shape segmentation via shape fully convolutional networks-----2018
3.模型生成
      1).Pixel2Mesh:Generating 3D mesh models from single RGB images-----2018
4.变形和编辑