Image: Qi et al
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Point cloud is an important type of geometric data structure.
Ranked #2 on Scene Segmentation on ScanNet
3D CLASSIFICATION 3D PART SEGMENTATION 3D POINT CLOUD CLASSIFICATION 3D SEMANTIC SEGMENTATION CLASSIFICATION OBJECT CLASSIFICATION SCENE SEGMENTATION SEMANTIC PARSING SKELETON BASED ACTION RECOGNITION
By exploiting metric space distances, our network is able to learn local features with increasing contextual scales.
Ranked #4 on Semantic Segmentation on ShapeNet
The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN.
Ranked #1 on 3D Instance Segmentation on S3DIS (mIoU metric)
Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices.
Ranked #5 on 3D Point Cloud Classification on ScanObjectNN
Furthermore, these locations are continuous in space and can be learned by the network.
Ranked #1 on Scene Segmentation on ScanNet (3DIoU metric)
Besides, our experiments converting CIFAR-10 into a point cloud showed that networks built on PointConv can match the performance of convolutional networks in 2D images of a similar structure.
Ranked #6 on Semantic Segmentation on ScanNet
Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others.
Ranked #14 on 3D Part Segmentation on ShapeNet-Part (Instance Average IoU metric)