融合全局注意力的图像裁剪方法：基于注意力引导与全局对齐的裁剪评估器
Global Attention-Fused Image Cropping with Attention-Guided and Global-Aligned Crop Evaluator
浏览论文内容
中文总结 AI 辅助
该研究提出GAFIC图像裁剪方法，通过AGFF与GACE模块结合多尺度排序损失，在GAIC、CPC数据集上性能优于现有方法，适用于需保证像素完整性与高效批量处理的场景。
中文摘要 AI 辅助
图像裁剪旨在通过在合适构图的区域内保留重要内容来提升图像美感。然而，现有大多数方法主要关注显著区域，因此对图像主要组件间的全局关系敏感度有限。为解决这一局限，我们提出融合全局注意力的图像裁剪方法（GAFIC），该方法包含注意力引导特征融合（AGFF）与全局对齐裁剪评估器（GACE）两个模块。AGFF聚合局部区域的重要性以构建全局表征，该表征同时捕捉图像结构与局部细节；GACE将候选裁剪特征与该全局表征对齐，使裁剪评估对边界变化保持敏感。我们进一步结合多尺度的三种排序损失以获得准确且稳定的裁剪得分。在GAIC与CPC数据集上开展的大量实验表明，GAFIC的性能优于现有图像裁剪方法，尤其在准确性与稳定性方面表现突出。与 seam carving、图像修复及扩散合成等像素级重定向方法不同，GAFIC不会合成或修改保留的像素，而是从源图像中选择审美偏好的裁剪结果，因此适用于像素完整性与高效批量处理至关重要的场景。源代码可在指定URL获取。
英文摘要
Image cropping aims to improve image aesthetics by preserving important content within an appropriately composed region. However, most existing methods focus primarily on salient regions and therefore have limited sensitivity to the global relationships among the main image components. To address this limitation, we propose Global Attention-Fused Image Cropping (GAFIC), which consists of an Attention-Guided Feature Fusion (AGFF) and a Global-Aligned Crop Evaluator (GACE). AGFF aggregates the importance of local regions to construct a global representation that captures both image structure and local details. GACE aligns candidate crop features with this global representation, enabling crop evaluation to remain sensitive to boundary changes. We further combine three ranking losses across multiple scales to obtain accurate and stable crop scores. Extensive experiments on the GAIC and CPC datasets demonstrate that GAFIC outperforms existing image-cropping methods, particularly in terms of accuracy and stability. Unlike pixel-level retargeting methods such as seam carving, inpainting, and diffusion-based synthesis, GAFIC does not synthesize or modify the retained pixels; instead, it selects an aesthetically preferred crop from the source image, making it suitable for scenarios where pixel integrity and efficient batch processing are important. The source code is available at https://github.com/AIVRC/GAFIC.git.
发表机构
- Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）
- Shenzhen University of Advanced Technology（深圳理工大学）
- Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
- The Hong Kong Polytechnic University（香港理工大学）
- Nantes Université（南特大学）
- Ecole Centrale Nantes（南特中央理工学院）
- CAPACITES SAS（CAPACITES SAS公司）
- CNRS（法国国家科学研究中心）
- LS2N, UMR 6004（LS2N实验室（UMR 6004））
机构由 AI 辅助整理，请以论文原文为准。
