Current depth map sensing technologies capture depth maps at low spatial resolution, rendering serious problems in various applications. In this paper, we propose a single depth map super-resolution method that combines the advantages of model-based methods and deep learning approaches. Specifically, we formulate a linear inverse problem which we solve by introducing a graph Laplacian regularizer. The regularization approach promotes smoothness and preserves the structural details of the observed depth map. We construct the graph Laplacian matrix by deploying latent features obtained from a pretrained deep learning model. The problem is solved with the Alternating Direction Method of Multipliers (ADMM). Experimental results show that the proposed approach outperforms existing optimization-based and deep learning solutions.
Gartzonikas, G, Tsiligianni, E, Deligiannis, N & Kondi, L 2025, 'A Graph Laplacian Regularizer from Deep Features for Depth Map Super-Resolution', Information, vol. 16, no. 6, 501, pp. 1-16. https://doi.org/10.3390/info16060501
Gartzonikas, G., Tsiligianni, E., Deligiannis, N., & Kondi, L. (2025). A Graph Laplacian Regularizer from Deep Features for Depth Map Super-Resolution. Information, 16(6), 1-16. Article 501. https://doi.org/10.3390/info16060501
@article{6f30b0874949441cbed64fb0f1389a92,
title = "A Graph Laplacian Regularizer from Deep Features for Depth Map Super-Resolution",
abstract = "Current depth map sensing technologies capture depth maps at low spatial resolution, rendering serious problems in various applications. In this paper, we propose a single depth map super-resolution method that combines the advantages of model-based methods and deep learning approaches. Specifically, we formulate a linear inverse problem which we solve by introducing a graph Laplacian regularizer. The regularization approach promotes smoothness and preserves the structural details of the observed depth map. We construct the graph Laplacian matrix by deploying latent features obtained from a pretrained deep learning model. The problem is solved with the Alternating Direction Method of Multipliers (ADMM). Experimental results show that the proposed approach outperforms existing optimization-based and deep learning solutions.",
keywords = "depth map super-resolution, graph-based regularization, alternating direction method of multipliers",
author = "George Gartzonikas and Evangelia Tsiligianni and Nikos Deligiannis and Lisimachos Kondi",
note = "Publisher Copyright: {\textcopyright} 2025 by the authors.",
year = "2025",
month = jun,
doi = "10.3390/info16060501",
language = "English",
volume = "16",
pages = "1--16",
journal = "Information",
issn = "2078-2489",
publisher = "MDPI AG",
number = "6",
}