Can We Use Neural Regularization to Solve Depth Super-Resolution?

TL;DR

This paper investigates the application of neural regularization in depth map super-resolution, revealing challenges and providing insights into its limitations compared to previous successes in photoacoustic tomography.

Contribution

It introduces a neural regularization approach for depth super-resolution and analyzes why it faces difficulties in this new domain.

Findings

Neural regularization is challenging to apply to depth super-resolution.

The approach was successful in photoacoustic tomography but not easily transferable.

The paper offers explanations for the difficulties encountered.

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.