Semi-supervised angular super-resolution method for autostereoscopic 3D surface measurement

Abstract

Autostereoscopic 3D measuring systems are an accurate, rapid, and portable method for in situ measurements. These systems use a micro-lens array to record 3D information based on the light-field theory. However, the spatial-angular-resolution trade-off curtails their performance. Although learning models were developed for super-resolution, the scarcity of data hinders efficient training. To address this issue, a novel, to the best of our knowledge, semi-supervised learning paradigm for angular super-resolution is proposed for data-efficient training, benefiting both autostereoscopic and light-field devices. A convolutional neural network using motion estimation is developed for a view synthesis. Subsequently, a high-angular-resolution autostereoscopic system is presented for an accurate profile reconstruction. Experiments show that the semi-supervision enhances view reconstruction quality, while the amount of training data required is reduced by over 69%.