Can We Use Neural Regularization to Solve Depth Super-Resolution?
This work addresses the problem of enhancing low-resolution depth maps for applications using commodity sensors, but it is incremental as it tests an existing method on a new domain with limited success.
The authors investigated whether a neural network-based Tikhonov regularization approach, previously successful in photoacoustic tomography, could be applied to depth map super-resolution, but found it difficult to implement effectively and provided reasons for the challenges.
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.