AI RESEARCH
Edge-Efficient Image Restoration: Transformer Distillation into State-Space Models
arXiv CS.CV
•
ArXi:2605.02794v1 Announce Type: new We propose a modular framework for hybrid image restoration that integrates transformer and state-space model (SSM) blocks with a focus on improving runtime efficiency on edge hardware. While transformers provide strong global modeling through self-attention, their attention kernels incur substantial latency on mobile devices, especially for high-resolution inputs. In contrast, SSMs such as Mamba offer lineartime sequence modeling with lower runtime overhead but may underperform on fine grained restoration tasks.