PU-Flow: a Point Cloud Upsampling Networkwith Normalizing Flows

07/13/2021
by   Aihua Mao, et al.
11

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 feature interpolation techniques to produce dense points uniformly distributed on the underlying surface. Specifically, we formulate the upsampling process as point interpolation in a latent space, where the interpolation weights are adaptively learned from local geometric context, and exploit the invertible characteristics of normalizing flows to transform points between Euclidean and latent spaces. We evaluate PU-Flow on a wide range of 3D models with sharp features and high-frequency details. Qualitative and quantitative results show that our method outperforms state-of-the-art deep learning-based approaches in terms of reconstruction quality, proximity-to-surface accuracy, and computation efficiency.

READ FULL TEXT

page 8

page 9

page 11

page 12

page 14

page 17

page 18

page 19

research
03/11/2022

PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows

Point cloud denoising aims to restore clean point clouds from raw observ...
research
02/24/2020

PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling

This paper addresses the problem of generating uniform dense point cloud...
research
06/01/2021

RAI-Net: Range-Adaptive LiDAR Point Cloud Frame Interpolation Network

LiDAR point cloud frame interpolation, which synthesizes the intermediat...
research
09/12/2022

Learning A Unified 3D Point Cloud for View Synthesis

3D point cloud representation-based view synthesis methods have demonstr...
research
02/14/2020

Pointfilter: Point Cloud Filtering via Encoder-Decoder Modeling

Point cloud filtering is a fundamental problem in geometry modeling and ...
research
04/22/2022

PU-EVA: An Edge Vector based Approximation Solution for Flexible-scale Point Cloud Upsampling

High-quality point clouds have practical significance for point-based re...
research
08/14/2020

Self-Sampling for Neural Point Cloud Consolidation

In this paper, we introduce a deep learning technique for consolidating ...

Please sign up or login with your details

Forgot password? Click here to reset