Semantics-aware transformer for 3D reconstruction from binocular images
Author:
Affiliation:

1. The Engineering Research Center of Learning-Based Intelligent System and the Key Laboratory of Computer Vision and System of Ministry of Education, Tianjin University of Technology, Tianjin 300384, China;2. Zhejiang University of Technology, Hangzhou 310014, China

Clc Number:

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    Existing multi-view three-dimensional (3D) reconstruction methods can only capture single type of feature from input view, failing to obtain fine-grained semantics for reconstructing the complex shapes. They rarely explore the semantic association between input views, leading to a rough 3D shape. To address these challenges, we propose a semantics-aware transformer (SATF) for 3D reconstruction. It is composed of two parallel view transformer encoders and a point cloud transformer decoder, and takes two red, green and blue (RGB) images as input and outputs a dense point cloud with richer details. Each view transformer encoder can learn a multi-level feature, facilitating characterizing fine-grained semantics from input view. The point cloud transformer decoder explores a semantically-associated feature by aligning the semantics of two input views, which describes the semantic association between views. Furthermore, it can generate a sparse point cloud using the semantically-associated feature. At last, the decoder enriches the sparse point cloud for producing a dense point cloud with richer details. Extensive experiments on the ShapeNet dataset show that our SATF outperforms the state-of-the-art methods.

    Reference
    Related
    Cited by
Get Citation

JIA Xin, YANGShourui, GUAN Diyi. Semantics-aware transformer for 3D reconstruction from binocular images[J]. Optoelectronics Letters,2022,18(5):293-299

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:April 04,2022
  • Revised:April 14,2022
  • Adopted:
  • Online: June 07,2022
  • Published: