Can We Use Neural Regularization to Solve Depth Super-Resolution?
Computer Vision and Pattern Recognition
2021-12-22 v1 Machine Learning
Abstract
Depth maps captured with commodity sensors often require super-resolution to be used in applications. In this work we study a super-resolution approach based on a variational problem statement with Tikhonov regularization where the regularizer is parametrized with a deep neural network. This approach was previously applied successfully in photoacoustic tomography. We experimentally show that its application to depth map super-resolution is difficult, and provide suggestions about the reasons for that.
Keywords
Cite
@article{arxiv.2112.11085,
title = {Can We Use Neural Regularization to Solve Depth Super-Resolution?},
author = {Milena Gazdieva and Oleg Voynov and Alexey Artemov and Youyi Zheng and Luiz Velho and Evgeny Burnaev},
journal= {arXiv preprint arXiv:2112.11085},
year = {2021}
}
Comments
9 pages