GMDepth: Depth Completion via Global Dense-to-Sparse Matching

Depth completion plays a key role in sensor-based measurement systems, as it facilitates the recovery of accurate and complete depth measurements from sparsely sampled sensor data. In this article, we revamp the prevailing depth completion paradigms such as classification-regression by formulating the task as a global dense-to-sparse matching problem. The proposed formulation completes missing pixels by matching each one to the optimal depth candidates among all sparse points. In order to instantiate it, we introduce a GMDepth framework, which involves three main components: an encoder–decoder network for feature extraction, successive cross-attention layers for feature enhancement, and a correlation-softmax layer for the global dense-to-sparse matching. Furthermore, we propose a self-induced calibration map to strengthen the robustness and stability of the matching process against sensor noise. Extensive experiments indicate that our method delivers superior performance compared to existing state-of-the-art methods, offering a promising solution for depth measurement tasks.