Channel Attention Based Iterative Residual Learning for Depth Map Super-Resolution

Citations Over TimeTop 10% of 2020 papers

Abstract

Despite the remarkable progresses made in deep learning based depth map super-resolution (DSR), how to tackle real-world degradation in low-resolution (LR) depth maps remains a major challenge. Existing DSR model is generally trained and tested on synthetic dataset, which is very different from what would get from a real depth sensor. In this paper, we argue that DSR models trained under this setting are restrictive and not effective in dealing with realworld DSR tasks. We make two contributions in tackling real-world degradation of different depth sensors. First, we propose to classify the generation of LR depth maps into two types: non-linear downsampling with noise and interval downsampling, for which DSR models are learned correspondingly. Second, we propose a new framework for real-world DSR, which consists of four modules : 1) An iterative residual learning module with deep supervision to learn effective high-frequency components of depth maps in a coarse-to-fine manner; 2) A channel attention strategy to enhance channels with abundant high-frequency components; 3) A multi-stage fusion module to effectively reexploit the results in the coarse-to-fine process; and 4) A depth refinement module to improve the depth map by TGV regularization and input loss. Extensive experiments on benchmarking datasets demonstrate the superiority of our method over current state-of-the-art DSR methods.

Related Papers

• → Depth Map Super-Resolution by Deep Multi-Scale Guidance(2016)348 cited
• → A novel upsampling scheme for depth map compression in 3DTV system(2010)21 cited
• → Depth map upsampling using depth local features(2014)9 cited
• → Depth upsampling methods for high resolution depth map(2018)2 cited
• → Low-Resolution Depth Map Upsampling Method Using Depth-Discontinuity Information(2013)1 cited