Open AccessImage Inpainting of Multi-Spectral Image with Laser Lines Based on Generative Adversarial Network
Author(s) -
Liang Lu,
Guoqiang Zhong,
Junyu Dong
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1880/1/012011
Subject(s) - inpainting , artificial intelligence , computer vision , rendering (computer graphics) , computer science , laser , line (geometry) , image (mathematics) , generative adversarial network , generative grammar , image restoration , pattern recognition (psychology) , image processing , optics , mathematics , physics , geometry
This paper presents a Generative Adversarial Network based on image in-painting, which can reconstruct the shape using a multi-spectral image with a laser line. One of the difficulties in multi-spectral photometric stereo is to extract the laser line, because the required illumination for multi-spectral photometric stereo, e.g. the red, green, and blue lights, may pollute the colour of the laser line. In this paper, we presents a method, which uses the Generative Adversarial Network based on image in-painting, to separate a multi-spectral image with a laser line into a clean laser image and an uncorrupted multi-spectral image without the laser line, to reconstruct the shape using a multi-spectral image with a laser line. To make the proposed method applicable to real-world objects, a rendered image dataset obtained using the rendering models in ShapeNet has been used for training the network, and the evaluation shows the superiority of the proposed approach over several previous methods, on both rendered images and real-world images.