SADG-Net: Sparse Adaptive Dynamic Guidance Network for Depth Completion

Hao Wu, Guodong Zhang, Chenchen Feng, Sifan Yang, Wenming Yang, Guijin Wang

Abstract: Existing depth completion methods with standard CNN and fixed guidance information often produce invalid value diffusion and mismatch between the guidance and the depth. To address this issue, we propose a SADG-Net for depth completion. Specifically, a sparse adaptive module is designed to infer the initial dense depth map and its confidence, as well as the affinity between pixels. Then we develop a dynamic guidance spatial propagation network to refine the initial depth map and dynamically update the guidance information with the inferred depth. In contrast to previous algorithms, our method effectively optimizes the processing for sparse depth and significantly alleviates the error accumulation issues in spatial propagation. Extensive experiments demonstrate that our model improves upon the state-of-the-art performance on NYUv2 and BIDCD datasets.