In the last few years, several works have tackled the problem of novel view synthesis from stereo images or even from a single picture. However, previous methods are computationally expensive, specially for high-resolution images. In this paper, we address the problem of generating a multiplane image (MPI) from a single high-resolution picture. We present the adaptive-MPI representation, which allows rendering novel views with low computational requirements. To this end, we propose an adaptive slicing algorithm that produces an MPI with a variable number of image planes. We present a new lightweight CNN for depth estimation, which is learned by knowledge distillation from a larger network. Occluded regions in the adaptive-MPI are inpainted also by a lightweight CNN. We show that our method is capable of producing high-quality predictions with one order of magnitude less parameters compared to previous approaches. The robustness of our method is evidenced on challenging pictures from the Internet.
@article{arxiv.2011.13317,
title = {Adaptive Multiplane Image Generation from a Single Internet Picture},
author = {Diogo C. Luvizon and Gustavo Sutter P. Carvalho and Andreza A. dos Santos and Jhonatas S. Conceicao and Jose L. Flores-Campana and Luis G. L. Decker and Marcos R. Souza and Helio Pedrini and Antonio Joia and Otavio A. B. Penatti},
journal= {arXiv preprint arXiv:2011.13317},
year = {2020}
}