Cluster-Based Autoencoders for Volumetric Point Clouds
This work addresses computational bottlenecks for researchers and practitioners working with high-resolution volumetric point clouds, though it appears incremental as it builds on existing methods like FoldingNet.
The authors tackled the problem of limited input size in autoencoders for volumetric point clouds by proposing a clustering and reassembling method, enabling high-resolution data input and demonstrating applications in blending and style transfer.
Autoencoders allow to reconstruct a given input from a small set of parameters. However, the input size is often limited due to computational costs. We therefore propose a clustering and reassembling method for volumetric point clouds, in order to allow high resolution data as input. We furthermore present an autoencoder based on the well-known FoldingNet for volumetric point clouds and discuss how our approach can be utilized for blending between high resolution point clouds as well as for transferring a volumetric design/style onto a pointcloud while maintaining its shape.