Structure-Aware Deep Unfolding Network for Face Super-Resolution with Global-Local Modeling

Face super-resolution aims to reconstruct high-resolution face images from the given low-resolution input, which has long been a research hotspot due to its wide-ranging applications. While deep learning has driven remarkable advances in this domain, existing approaches still face two fundamental limitations. First, existing methods often function as black-box systems with limited interpretability and transparency in their internal representations and feature learning behavior. This limits the ability to understand and improve the model’s decision making process, then weakening the model’s trustworthiness. Second, both global and local information are essential for high-fidelity face reconstruction, existing methods still struggle to effectively model these complementary dependencies. To address these challenges, we propose an optimization-inspired structure-aware deep unfolding framework for face super-resolution. Specifically, we formulate the face reconstruction task as an explicit optimization problem and unfold its iterative solution into a deep neural network, where each stage corresponds to a well-defined optimization step with clear physical interpretation, enhancing model’s trustworthiness. To enable efficient global-local feature modeling within our unfolding framework, we propose a structure-aware Receptance Weighted Key-Value (RWKV)-based proximal operator, which leverages the linear-complexity architecture of RWKV for global context modeling. Furthermore, we design a structure-aware deformable shift mechanism to enhance its ability for preserving fine-grained facial geometry, which can dynamically adjust spatial aggregation patterns based on the facial structure to effectively capture local information. Extensive experiments conducted on benchmark datasets demonstrate that our method outperforms state-of-the-art approaches in both quantitative metrics and visual quality.