%A Ariav,Ido %A Cohen,Israel %D 2022 %J Frontiers in Signal Processing %C %F %G English %K Depth maps,super-resolution,deep learning,Attention,transformers %Q %R 10.3389/frsip.2022.847890 %W %L %M %P %7 %8 2022-March-24 %9 Original Research %# %! Depth Map Super-Resolution %* %< %T Depth Map Super-Resolution via Cascaded Transformers Guidance %U https://www.frontiersin.org/articles/10.3389/frsip.2022.847890 %V 2 %0 JOURNAL ARTICLE %@ 2673-8198 %X Depth information captured by affordable depth sensors is characterized by low spatial resolution, which limits potential applications. Several methods have recently been proposed for guided super-resolution of depth maps using convolutional neural networks to overcome this limitation. In a guided super-resolution scheme, high-resolution depth maps are inferred from low-resolution ones with the additional guidance of a corresponding high-resolution intensity image. However, these methods are still prone to texture copying issues due to improper guidance by the intensity image. We propose a multi-scale residual deep network for depth map super-resolution. A cascaded transformer module incorporates high-resolution structural information from the intensity image into the depth upsampling process. The proposed cascaded transformer module achieves linear complexity in image resolution, making it applicable to high-resolution images. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art techniques for guided depth super-resolution.