DeepAI AI Chat
Log In Sign Up

Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis

by   Qijian Zhang, et al.
City University of Hong Kong
Nanyang Technological University

Point clouds are characterized by irregularity and unstructuredness, which pose challenges in efficient data exploitation and discriminative feature extraction. In this paper, we present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology as a completely regular 2D point geometry image (PGI) structure, in which coordinates of spatial points are captured in colors of image pixels. Intuitively, Flattening-Net implicitly approximates a locally smooth 3D-to-2D surface flattening process while effectively preserving neighborhood consistency. As a generic representation modality, PGI inherently encodes the intrinsic property of the underlying manifold structure and facilitates surface-style point feature aggregation. To demonstrate its potential, we construct a unified learning framework directly operating on PGIs to achieve diverse types of high-level and low-level downstream applications driven by specific task networks, including classification, segmentation, reconstruction, and upsampling. Extensive experiments demonstrate that our methods perform favorably against the current state-of-the-art competitors. We will make the code and data publicly available at


page 3

page 5

page 15


ParaNet: Deep Regular Representation for 3D Point Clouds

Although convolutional neural networks have achieved remarkable success ...

Surface Representation for Point Clouds

Most prior work represents the shapes of point clouds by coordinates. Ho...

GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation

The recent neural implicit representation-based methods have greatly adv...

Learning to Segment 3D Point Clouds in 2D Image Space

In contrast to the literature where local patterns in 3D point clouds ar...

GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning

In the realm of 3D-computer vision applications, point cloud few-shot le...

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

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

Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds

Point normal, as an intrinsic geometric property of 3D objects, not only...