{"ID":2881582,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.11893","arxiv_id":"2508.11893","title":"Large Kernel Modulation Network for Efficient Image Super-Resolution","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.","short_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 p...","url_abs":"https://arxiv.org/abs/2508.11893","url_pdf":"https://arxiv.org/pdf/2508.11893v1","authors":"[\"Quanwei Hu\",\"Yinggan Tang\",\"Xuguang Zhang\"]","published":"2025-08-16T03:43:14Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"eess.IV\"]","methods":"[\"Transformer\",\"Convolutional Neural Network\"]","has_code":false,"code_links":[{"ID":610824,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2881582,"paper_url":"https://arxiv.org/abs/2508.11893","paper_title":"Large Kernel Modulation Network for Efficient Image Super-Resolution","repo_url":"https://github.com/Supereeeee/LKMN","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}