{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ppformer-using-pixel-wise-and-patch-wise","title":"PPformer: Using pixel-wise and patch-wise cross-attention for low-light image enhancement","arxiv_id":null,"date":"2024-01-15","proceeding":"Computer Vision and Image Understanding 2024 1","authors":["J Dang","Y Zhong","X Qin"],"abstract":"Recently, transformer-based methods have shown strong competition compared to CNN-based methods on the low-light image enhancement task, by employing the self-attention for feature extraction. Transformer-based methods perform well in modeling long-range pixel dependencies, which are essential for low-light image enhancement to achieve better lighting, natural colors, and higher contrast. However, the high computational cost of self-attention limits its development in low-light image enhancement, while some works struggle to balance accuracy and computational cost. In this work, we propose a lightweight and effective network based on the proposed pixel-wise and patch-wise cross-attention mechanism, PPformer, for low-light image enhancement. PPformer is a CNN-transformer hybrid network that is divided into three parts: local-branch, global-branch, and Dual Cross-Attention. Each part plays a vital role in PPformer. Specifically, the local-branch extracts local structural information using a stack of Wide Enhancement Modules, and the global-branch provides the refining global information by Cross Patch Module and Global Convolution Module. Besides, different from self-attention, we use extracted global semantic information to guide modeling dependencies between local and non-local. According to calculating Dual Cross-Attention, the PPformer can effectively restore images with better color consistency, natural brightness and contrast. Benefiting from the proposed dual cross-attention mechanism, PPformer effectively captures the dependencies in both pixel and patch levels for a full-size feature map. Extensive experiments on eleven real-world benchmark datasets show that PPformer achieves better quantitative and qualitative results than previous state-of-the-art methods.","url_abs":"https://www.sciencedirect.com/science/article/abs/pii/S1077314224000110","url_pdf":"https://www.sciencedirect.com/science/article/abs/pii/S1077314224000110","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ppformer-using-pixel-wise-and-patch-wise","repo_url":"https://github.com/DeniJsonC/PPformer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"low-light-image-enhancement","task_name":"Low-Light Image Enhancement"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/low-light-image-enhancement-on-lol","task":"Low-Light Image Enhancement","dataset":"LOL","model":"PPformer","rank_in_archive_order":26,"of":40,"metrics":{"Average PSNR":"23.91","LPIPS":"0.12","SSIM":"0.841"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}