{"ID":6537672,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11088","arxiv_id":"2607.11088","title":"CUST: Clustered Unit-level Similarity Transformer for Lightweight Image Super-Resolution","abstract":"Recently, Vision Transformer (ViT)-based models have exhibited remarkable performance in image super-resolution. However, the quadratic computational complexity of ViTs with respect to spatial resolution severely constrains their efficiency, leading to high latency and massive memory consumption. To alleviate this, various window-based attention mechanisms have been proposed; yet, they inherently compromise the long-range dependency modeling that is the primary advantage of ViTs. To overcome these limitations, we propose the Clustered Unit-level Similarity Transformer (CUST), a novel architecture that efficiently integrates global and local information. Specifically, CUST enables each patch to aggregate and attend to similar patches within a broadened regional scope outside its local window, thereby capturing extensive contextual understanding. Furthermore, it employs overlapping attention windows to capture local dependencies, while explicitly extracting high-frequency details by computing the residual difference between the original features and their downsampled-upsampled counterparts. Comprehensive experiments demonstrate that our proposed model achieves a practical balance between computational efficiency and restoration performance. It achieves a lower memory footprint and faster inference speed compared to recent global context or lightweight models under realistic constraints. Code is available at [https://github.com/jwgdmkj/CUST].","short_abstract":"Recently, Vision Transformer (ViT)-based models have exhibited remarkable performance in image super-resolution. However, the quadratic computational complexity of ViTs with respect to spatial resolution severely constrains their efficiency, leading to high latency and massive memory consumption. To alleviate this, var...","url_abs":"https://arxiv.org/abs/2607.11088","url_pdf":"https://arxiv.org/pdf/2607.11088v1","authors":"[\"Jeongsoo Kim\"]","published":"2026-07-13T04:56:57Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Vision Transformer\",\"Transformer\"]","has_code":false,"code_links":[{"ID":614222,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-14T02:54:43.516908796Z","DeletedAt":null,"paper_id":6537672,"paper_url":"https://arxiv.org/abs/2607.11088","paper_title":"CUST: Clustered Unit-level Similarity Transformer for Lightweight Image Super-Resolution","repo_url":"https://github.com/jwgdmkj/CUST","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}