• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Zhang, Jiahui (Zhang, Jiahui.) | Yang, Jinfu (Yang, Jinfu.) (Scholars:杨金福) | Fu, Fuji (Fu, Fuji.) | Ma, Jiaqi (Ma, Jiaqi.)

Indexed by:

EI Scopus SCIE

Abstract:

Planar 3D reconstruction aims to simultaneously extract plane instances and reconstruct the local 3D model through the estimated plane parameters. Existing methods achieve promising results either through selfattention or convolution neural network (CNNs), but usually ignore the complementary properties of them. In this paper, we propose a line -guided planar 3D reconstruction method PlaneAC, which leverages the advantage of self -attention and CNNs to capture long-range dependencies and alleviate the computational burden. In addition, explicit connection between two adjacent attention layers is built for better leveraging the transferable knowledge and facilitating the information flow between tokenized feature from different layers. Therefore, the subsequent attention layer can directly interact with previous results. Finally, a line segment filtering method is presented to remove irrelevant guiding information from indistinctive line segments extracted from the image. Extensive experiments on ScanNet and NYUv2 public datasets demonstrate the preferable performance of our proposed method, and the results show that PlaneAC achieves a better trade-off between accuracy and computation cost compared with other state-of-the-art methods.

Keyword:

Transferable knowledge Line segments Self-attention Planar 3D reconstruction Convolution neural network

Author Community:

  • [ 1 ] [Zhang, Jiahui]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Yang, Jinfu]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 3 ] [Fu, Fuji]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 4 ] [Ma, Jiaqi]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 5 ] [Yang, Jinfu]Beijing Univ Technol, Beijing Key Lab Computat Intelligence & Intelligen, Beijing 100124, Peoples R China
  • [ 6 ] [Yang, Jinfu]Beijing Univ Technol, 100,Pingleyuan,Chaoyang Dist, Beijing, Peoples R China

Reprint Author's Address:

  • [Yang, Jinfu]Beijing Univ Technol, 100,Pingleyuan,Chaoyang Dist, Beijing, Peoples R China;;

Show more details

Related Keywords:

Related Article:

Source :

PATTERN RECOGNITION

ISSN: 0031-3203

Year: 2024

Volume: 153

8 . 0 0 0

JCR@2022

Cited Count:

WoS CC Cited Count:

SCOPUS Cited Count: 5

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Affiliated Colleges:

Online/Total:664/5314533
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.