AI RESEARCH
FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution
arXiv CS.CV
•
ArXi:2506.14121v2 Announce Type: replace Face super-resolution (FSR) under limited computational budgets remains challenging. Existing methods often treat all facial pixels equally, leading to suboptimal resource allocation and degraded performance. CNNs are sensitive to high-frequency facial features such as contours and outlines, while Mamba excels at capturing low-frequency attributes like facial color and texture with lower complexity than Transformers.