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

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

5 Scopus Citations
View graph of relations


Original languageEnglish
Pages (from-to)9726-9742
Journal / PublicationIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number8
Online published14 Feb 2023
Publication statusPublished - Aug 2023


Point clouds are characterized by irregularity and un-structuredness, 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.

© 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.

Research Area(s)

  • Point cloud compression, Three-dimensional displays, Feature extraction, Geometry, Task analysis, Surface treatment, Solid modeling