构建高分辨率多目标图像裁剪数据集，助力社交媒体图片自动优化
Carousel: A High-Resolution Dataset for Multi-Target Automatic Image Cropping
- 设计图像分割预处理+单裁剪模型，实现多目标高质量裁剪
- 收集277张真实场景图，含人工标注的审美偏好标签
- 适合做多目标图像生成、社交平台视觉优化的研究者参考
自动图像裁剪旨在最大化照片裁剪区域的人类感知质量。尽管已有若干方法可生成单一裁剪结果，但针对多个不同且具有审美吸引力的裁剪方案的研究仍较少。本文通过分析现代社交媒体应用的需求，提出一个包含277张相关图像及人工标注的高质量数据集，并评估了多种单裁剪模型在图像分割预处理后的表现。该数据集已公开于https://github.com/RafeLoya/carousel。
原文摘要 · Abstract (English)
Automatic image cropping is a method for maximizing the human-perceived quality of cropped regions in photographs. Although several works have proposed techniques for producing singular crops, little work has addressed the problem of producing multiple, distinct crops with aesthetic appeal. In this paper, we motivate the problem with a discussion on modern social media applications, introduce a dataset of 277 relevant images and human labels, and evaluate the efficacy of several single-crop models with an image partitioning algorithm as a pre-processing step. The dataset is available at https://github.com/RafeLoya/carousel.
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。