Digging into depth-adaptive structure for guided depth super-resolution

Yue Hou, Lang Nie, Chunyu Lin, Baoqing Guo, Yao Zhao

Abstract: Highlights•We introduce a novel Hybrid Encoder that amalgamates different network architectures for multi-stage feature extraction. This enables a robust and comprehensive feature representation.•We present Feature Adjustment and Fusion Module (FAFM) to optimize the high-frequency signals of the RGB image by bridging them with the high-frequency signals of the depth map via a cross-modal attention mechanism, thus focusing on the depth-related structure in RGB.•The experimental results show that our DASNet obtains quality improvement on depth maps and synthesized views, compared with state-of-the-art methods.