Deep Magnification-Arbitrary Upsampling over 3D Point Clouds

11/25/2020
by   Yue Qian, et al.
6

This paper addresses the problem of generating dense point clouds from given sparse point clouds to model the underlying geometric structures of objects/scenes. To tackle this challenging issue, we propose a novel end-to-end learning based framework, namely MAPU-Net. Specifically, by taking advantage of the linear approximation theorem, we first formulate the problem explicitly, which boils down to determining the interpolation weights and high-order approximation errors. Then, we design a lightweight neural network to adaptively learn unified and sorted interpolation weights and normal-guided displacements, by analyzing the local geometry of the input point cloud. MAPU-Net can be interpreted by the explicit formulation, and thus is more memory-efficient than existing ones. In sharp contrast to the existing methods that work only for a pre-defined and fixed upsampling factor, MAPU-Net, a single neural network with one-time training, can handle an arbitrary upsampling factor, which is highly desired in real-world applications. In addition, we propose a simple yet effective training strategy to drive such a flexible ability. Extensive experiments on both synthetic and real world data demonstrate the superiority of the proposed MAPU-Net over state-of-the-art methods both quantitatively and qualitatively. To the best of our knowledge, this is the first end-to-end learning based method that is capable of achieving magnification-arbitrary upsampling over 3D point clouds.

READ FULL TEXT

page 1

page 7

page 8

page 9

page 10

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
12/31/2020

CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds

This paper addresses the problem of computing dense correspondence betwe...
research
11/28/2019

Geometric Feedback Network for Point Cloud Classification

As the basic task of point cloud learning, classification is fundamental...
research
02/25/2021

A Simulation-based End-to-End Learning Framework for Evidential Occupancy Grid Mapping

Evidential occupancy grid maps (OGMs) are a popular representation of th...
research
12/17/2020

FG-Net: Fast Large-Scale LiDAR Point CloudsUnderstanding Network Leveraging CorrelatedFeature Mining and Geometric-Aware Modelling

This work presents FG-Net, a general deep learning framework for large-s...
research
03/22/2022

IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment

This paper investigates the problem of temporally interpolating dynamic ...
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...

Please sign up or login with your details

Forgot password? Click here to reset