FSM-Net: An Efficient Frequency-Spatial Network for Real-World Deblurring
This work provides a highly efficient and effective deblurring solution for applications with resource constraints, such as mobile devices or real-time systems, by pushing the Pareto frontier of efficiency and quality.
This paper introduces FSM-Net, a novel network for real-world image deblurring that achieves a PSNR of 33.144 dB on the RSBlur benchmark while maintaining high efficiency with only 4.94M parameters and 159.35 GMACs. It tackles the problem of balancing high-fidelity restoration and computational efficiency in deblurring.
Real-world image deblurring demands both high-fidelity restoration and computational efficiency, a balance existing methods often struggle to achieve. In this paper, we propose FSM-Net (Frequency-Spatial Multi-branch Network), a highly efficient solution that secured 2nd place in the NTIRE 2026 Challenge on Efficient Real-World Deblurring. FSM-Net pioneers a dual-domain approach: a novel Frequency Attention module explicitly recovers high-frequency structural details via FFT, while a Cross-Gated Vision E-Branchformer at the bottleneck captures global dependencies with linear complexity. To ensure robust convergence, we employ a progressive curriculum training strategy guided by a composite loss function (Multi-Scale Charbonnier, Structural Edge, and Frequency). Evaluated on the RSBlur benchmark, FSM-Net achieves an outstanding 33.144 dB PSNR with only 4.94M parameters and 159.35 GMACs (at 1920x1200 resolution). By effectively pushing the Pareto frontier of efficiency and quality, FSM-Net establishes a strong baseline for resource-constrained image restoration.