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

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

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 arbitrar...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 8 vom: 13. Aug., Seite 9726-9742
Auteur principal: Zhang, Qijian (Auteur)
Autres auteurs: Hou, Junhui, Qian, Yue, Zeng, Yiming, Zhang, Juyong, He, Ying
Format: Article en ligne
Langue:English
Publié: 2023
Accès à la collection:IEEE transactions on pattern analysis and machine intelligence
Sujets:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM355275597
003 DE-627
005 20250304151726.0
007 cr uuu---uuuuu
008 231226s2023 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2023.3244828  |2 doi 
028 5 2 |a pubmed25n1183.xml 
035 |a (DE-627)NLM355275597 
035 |a (NLM)37022866 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Zhang, Qijian  |e verfasserin  |4 aut 
245 1 0 |a Flattening-Net  |b Deep Regular 2D Representation for 3D Point Cloud Analysis 
264 1 |c 2023 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 03.07.2023 
500 |a Date Revised 03.07.2023 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a 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 
650 4 |a Journal Article 
700 1 |a Hou, Junhui  |e verfasserin  |4 aut 
700 1 |a Qian, Yue  |e verfasserin  |4 aut 
700 1 |a Zeng, Yiming  |e verfasserin  |4 aut 
700 1 |a Zhang, Juyong  |e verfasserin  |4 aut 
700 1 |a He, Ying  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 45(2023), 8 vom: 13. Aug., Seite 9726-9742  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:45  |g year:2023  |g number:8  |g day:13  |g month:08  |g pages:9726-9742 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2023.3244828  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 45  |j 2023  |e 8  |b 13  |c 08  |h 9726-9742