3D visualization model construction based on generative adversarial networks

Xiaojuan Liu; Shangbo Zhou; Sheng Wu; Duo Tan; Rui Yao

doi:10.7717/peerj-cs.768

3D visualization model construction based on generative adversarial networks

PeerJ Comput Sci. 2022 Mar 29:8:e768. doi: 10.7717/peerj-cs.768. eCollection 2022.

Authors

Xiaojuan Liu^#¹, Shangbo Zhou^#², Sheng Wu³, Duo Tan³, Rui Yao³

Affiliations

¹ College of Computer Science, Chongqing University, Chongqing, China.
² Key Laboratory of Dependable Service Computing in Cyber Physical Society, Ministry of Education, Chongqing University, Chongqing, China.
³ College of Computer and Information Science, SouthWest University, Chongqing, China.

^# Contributed equally.

Abstract

The development of computer vision technology is rapid, which supports the automatic quality control of precision components efficiently and reliably. This paper focuses on the application of computer vision technology in manufacturing quality control. A new deep learning algorithm is presented, Multi-angle projective Generative Adversarial Networks (MapGANs), to automatically generate 3D visualization models of products and components. The generated 3D visualization models can intuitively and accurately display the product parameters and indicators. Based on these indicators, our model can accurately determine whether the product meets the standard. The working principle of the MapGANs algorithm is to automatically infer the basic three-dimensional shape distribution through the product's projection module, while using multiple angles and multiple views to improve the fineness and accuracy of the three-dimensional visualization model. The experimental results prove that MapGANs can effectively reconstruct two-dimensional images into three-dimensional visualization models, and meanwhile accurately predict whether the quality of the product meets the standard.

Keywords: 3D visualization model; Generation adversarial network; Neural network; Precision components.

Grants and funding

This work was supported by the National Natural Science Foundation of China under Grant 41271292, by the China Postdoctoral Science Foundation under Grant 2015M580765, by the Chongqing Postdoctoral Science Foundation under Grant Xm2016041, by the Fundamental Research Funds for the Central Universities, China under Grant XDJK2018B020, and by the National Social Science Foundation of China under Grant 19BYY171. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.