Adaptive Multiplane Image Generation from a Single Internet Picture

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 imag...

Full description

Saved in:
Bibliographic Details
Main Authors: Luvizon, Diogo C., Carvalho, Gustavo Sutter P., dos Santos, Andreza A., Conceicao, Jhonatas S., Flores-Campana, Jose L., Decker, Luis G. L., Souza, Marcos R., Pedrini, Helio, Joia, Antonio, Penatti, Otavio A. B.
Format: Conference Proceeding
Language:English
Subjects:
Adaptation models
Computational modeling
Conferences
Estimation
Image representation
Image synthesis
Knowledge engineering
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2642-9381
DOI:10.1109/WACV48630.2021.00260