Large Kernel Modulation Network for Efficient Image Super-Resolution

TL;DR

The paper introduces LKMN, a CNN-based model with large kernel modules and cross-gate mechanisms, achieving superior image super-resolution performance with reduced complexity and faster inference.

Contribution

Proposes the Large Kernel Modulation Network (LKMN), combining large kernel convolutions and cross-gate fusion to enhance super-resolution while maintaining efficiency.

Findings

Outperforms state-of-the-art lightweight SR models.

Achieves 0.23 dB PSNR improvement on Manga109 dataset.

Nearly 4.8 times faster inference than comparable models.

Abstract

Image super-resolution (SR) in resource-constrained scenarios demands lightweight models balancing performance and latency. Convolutional neural networks (CNNs) offer low latency but lack non-local feature capture, while Transformers excel at non-local modeling yet suffer slow inference. To address this trade-off, we propose the Large Kernel Modulation Network (LKMN), a pure CNN-based model. LKMN has two core components: Enhanced Partial Large Kernel Block (EPLKB) and Cross-Gate Feed-Forward Network (CGFN). The EPLKB utilizes channel shuffle to boost inter-channel interaction, incorporates channel attention to focus on key information, and applies large kernel strip convolutions on partial channels for non-local feature extraction with reduced complexity. The CGFN dynamically adjusts discrepancies between input, local, and non-local features via a learnable scaling factor, then employs a cross-gate strategy to modulate and fuse these features, enhancing their complementarity. Extensive experiments demonstrate that our method outperforms existing state-of-the-art (SOTA) lightweight SR models while balancing quality and efficiency. Specifically, LKMN-L achieves 0.23 dB PSNR improvement over DAT-light on the Manga109 dataset at $\times$4 upscale, with nearly $\times$4.8 times faster. Codes are in the supplementary materials. The code is available at https://github.com/Supereeeee/LKMN.