Transcription of PAConv: Position Adaptive Convolution With Dynamic Kernel ...
{{id}} {{{paragraph}}}
Example: air traffic controller
PAConv: Position Adaptive Convolution With Dynamic Kernel ...
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling onPoint CloudsMutian Xu1*Runyu Ding1*Hengshuang Zhao2 Xiaojuan Qi1 1 The University of Hong Kong2 University of introducePositionAdaptive Convolution (PAConv),a generic Convolution operation for 3D point cloud process-ing. The key of PAConv is to construct the Convolution ker-nel by dynamically assembling basic weight matrices storedin Weight Bank, where the coefficients of these weight matri-ces are self-adaptively learned from point positions throughScoreNet. In this way, the Kernel is built in a data-drivenmanner, endowing PAConv with more flexibility than 2 Dconvolutions to better handle the irregular and unorderedpoint cloud data. Besides, the complexity of the learningprocess is reduced by combining weight matrices instead ofbrutally predicting kernels from point , different from the existing point convolu-tion operators whose network architectures are often heav-ily engineered, we integrate our PAConv into classicalMLP-based point cloud pipelineswithoutchanging net-work configurations.
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds Mutian Xu1* Runyu Ding1* Hengshuang Zhao2 Xiaojuan Qi1† 1The University of Hong Kong 2University of Oxford mino1018@outlook.com, {ryding, xjqi}@eee.hku.hk, hengshuang.zhao@eng.ox.ac.uk
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: