The proposed method effectively considers all the elements in each dimension and models the nonlinear interactions between feature dimensions as complementary information to max-pooling. To this end, this paper proposes a novel kernel-based feature aggregation framework for 3D point cloud analysis for the first time. The desired advanced method should be capable of modeling richer information between the point features than max-pooling, and, at the same time, it can readily replace max-pooling without the need to modify other parts of the existing network architecture. These drawbacks of max-pooling motivate us to explore advanced feature aggregation methods for 3D point cloud analysis. However, while enjoying simplicity and high efficiency, max-pooling does not fully exploit the feature information since it not only ignores the non-maximum elements in each feature dimension but also neglects the interactions between different dimensions. As a typical order-invariant aggregation method, max-pooling has been widely applied. One key step in these networks is to aggregate the features of orderless points into a compact representation for the cloud. Various effective deep networks have been developed for analysis of 3D point clouds.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |