高效生成多区域不重叠图像裁剪，提升自动裁剪实用性。
Efficient Multi-Crop Saliency Partitioning for Automatic Image Cropping
- 动态调整注意力阈值，逐次提取多个不重叠裁剪区域。
- 线性时间复杂度，无需重复计算整个显著图。
- 适合需要多裁剪输出的场景，如画廊布局、广告排版。
自动图像裁剪旨在提取最具视觉显著性的区域，同时保留关键构图元素。传统显著性感知裁剪方法仅优化单个边界框，在需要多个分离裁剪的应用中效果不佳。本文将固定长宽比裁剪算法扩展为高效提取多个非重叠裁剪区域的方法，实现线性时间复杂度。该方法通过动态调整注意力阈值，并在选取裁剪区域后将其从后续考虑中移除，无需重新计算整个显著图。我们展示了定性结果，并探讨了未来构建专用数据集和基准的潜力。
原文摘要 · Abstract (English)
Automatic image cropping aims to extract the most visually salient regions while preserving essential composition elements. Traditional saliency-aware cropping methods optimize a single bounding box, making them ineffective for applications requiring multiple disjoint crops. In this work, we extend the Fixed Aspect Ratio Cropping algorithm to efficiently extract multiple non-overlapping crops in linear time. Our approach dynamically adjusts attention thresholds and removes selected crops from consideration without recomputing the entire saliency map. We discuss qualitative results and introduce the potential for future datasets and benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。