Implicit neural network-based coal SEM super-resolution for enhancing micro-pores measurement tasks.

Prolonged radiation exposure in coal Scanning Electron Microscopy (SEM) poses structural damage risks to specimens during high-resolution observation. To mitigate this situation, we propose an interactive-interpretable super-resolution (SR) framework that integrates implicit neural representation (INR) with model-driven Half-Quadratic Splitting (HQS) optimization. Specifically, the implicit neural representation employs a local window attention mechanism to capture contextual dependencies across reconstructed regions. Furthermore, an interactive dual-branch network decouples feature content and positional encoding, providing an initial solution for the subsequent HQS optimization. By unfolding the HQS algorithm into a deep network, each layer corresponds to an explicit and interpretable optimization step with the explicit mathmatical transparency. Experimental results demonstrate that our method outperforms the related state-of-the-art SR algorithms in visual fidelity and exhibits the applicability and stability in downstream geometry-sensitive measurement tasks.