PU-Flow: a Point Cloud Upsampling Network with Normalizing Flows
This addresses the problem of generating high-quality dense point clouds for applications like 3D reconstruction and computer vision, representing an incremental improvement over existing methods.
The paper tackles point cloud upsampling by proposing PU-Flow, a deep learning model that uses normalizing flows and weight prediction to generate dense, uniformly distributed points from sparse inputs, achieving competitive or superior performance in reconstruction quality, accuracy, and efficiency compared to state-of-the-art methods.
Point cloud upsampling aims to generate dense point clouds from given sparse ones, which is a challenging task due to the irregular and unordered nature of point sets. To address this issue, we present a novel deep learning-based model, called PU-Flow, which incorporates normalizing flows and weight prediction techniques to produce dense points uniformly distributed on the underlying surface. Specifically, we exploit the invertible characteristics of normalizing flows to transform points between Euclidean and latent spaces and formulate the upsampling process as ensemble of neighbouring points in a latent space, where the ensemble weights are adaptively learned from local geometric context. Extensive experiments show that our method is competitive and, in most test cases, it outperforms state-of-the-art methods in terms of reconstruction quality, proximity-to-surface accuracy, and computation efficiency. The source code will be publicly available at https://github.com/unknownue/pu-flow.