Can We Use Neural Regularization to Solve Depth Super-Resolution?
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 21 references that are in the map. First posted on arXiv 21 Dec 2021.
Builds on
12 of 21 references.
References · 12
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
- 2020Knowledge Distillation: A Surveycited by 1,578
- 2015A Neural Algorithm of Artistic Stylecited by 480
- 2018Adversarial Regularizers in Inverse Problemscited by 102
- 2018NETT: Solving Inverse Problems with Deep Neural Networkscited by 89
- 2020Channel Attention based Iterative Residual Learning for Depth Map Super-Resolutioncited by 40
- 2019'Zhores' -- Petaflops supercomputer for data-driven modeling, machine learning and artificial intelligence installed in Skolkovo Institute of Science and Technologycited by 23
- 2015Bilevel parameter learning for higher-order total variation regularisation modelscited by 14
- 2018Photometric Depth Super-Resolutioncited by 8
- 2014Revisiting loss-specific training of filter-based MRFs for image restorationcited by 3
Built on by
Not cited yet.