English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We introduce Position Adaptive Convolution (PAConv), a generic convolutionoperation for 3D point cloud processing. The key of PAConv is to construct theconvolution kernel by dynamically assembling basic weight matrices stored inWeight Bank, where the coefficients of these weight matrices areself-adaptively learned from point positions through ScoreNet. In this way, thekernel is built in a data-driven manner, endowing PAConv with more flexibilitythan 2D convolutions to better handle the irregular and unordered point clouddata. Besides, the complexity of the learning process is reduced by combiningweight matrices instead of brutally predicting kernels from point positions.  Furthermore, different from the existing point convolution operators whosenetwork architectures are often heavily engineered, we integrate our PAConvinto classical MLP-based point cloud pipelines without changing networkconfigurations. Even built on simple networks, our method still approaches oreven surpasses the state-of-the-art models, and significantly improves baselineperformance on both classification and segmentation tasks, yet with decentefficiency. Thorough ablation studies and visualizations are provided tounderstand PAConv. Code is released on https://github.com/CVMI-Lab/PAConv.

PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds