狂读专题
【点云处理之论文狂读经典版11】—— Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
KCNet: Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling 摘要引言方法Learning on Local Geometric StructureLearning on Local Feature Structure 实验Shape ClassificationPart Segmenta
【点云处理之狂读论文经典篇2】——Multi-view Convolutional Neural Networks for 3D Shape Recognition
MVCNN：一种用于3D形状识别的多视图卷积神经网络 摘要1. 引言2. 相关工作3. 方法3.1 Input: A Multi-view Representation3.2 Recognition with Multi-view Representations3.3 Multi-view CNN: Learning to Aggregate Views 4. 实验4.1 3D Shape
【点云处理之论文狂读经典版14】—— Dynamic Graph CNN for Learning on Point Clouds
DGCNN：Dynamic Graph CNN for Learning on Point Clouds 摘要方法Edge ConvolutionDynamic Graph UpdateProperties 实验ClassificationPart SegmentationIndoor Scene Segmentation 展望生词 摘要 背景： 对于计算机图形学中的许多应用而言
【点云处理之论文狂读前沿版1】——Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP
重新审视点云处理中的网络设计和局部几何结构——一个简单的残差MLP框架 1.摘要2.引言2.相关工作3.方法3.1 Revisiting point-based methods3.2 PointMLP的框架结构3.3 Geometric Affine Module3.4 计算复杂度和Elite版 4.实验4.1 Shape classification on ModelNet4.2 Shap