arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.02268cs.CVcs.MM
收藏

基于多块保持内容原始宽高比的图像美学预测

Image Aesthetics Prediction Using Multiple Patches Preserving the Original Aspect Ratio of Contents

The University of Tokyo(东京大学)

Lijie Wang, Xueting Wang, Toshihiko Yamasaki

摘要:

社交网络服务的普及创造了对选择、编辑和生成令人印象深刻的图像的日益增长的需求。这种趋势增加了评价图像美学作为自动图像处理的补充功能的重要性。我们提出了一个多补丁的方法,命名为MPA-Net(多补丁聚合网络),预测图像美学分数保持原来的长宽比的内容在图像中。通过涉及大规模AVA数据集,其中包含250,000张图像的实验,我们表明,与单块预测和随机块选择方法相比,等间隔多块选择方法用于美学评分预测的有效性是显着的。对于该数据集,MPA-Net优于神经图像评估算法,后者被视为基线方法。特别是,MPA-Net产生了0.073(11.5%)更高的线性相关系数(LCC)的美学评分和0.088(14.4%)更高的斯皮尔曼等级相关系数(SRCC)。MPA-Net还将均方误差(MSE)降低了0.0115(4.18%),并实现了与最先进的连续美学评分预测方法相当的LCC和SRCC结果。最值得注意的是,MPA-Net产生了显着较低的MSE,特别是对于宽高比远离1.0的图像,这表明MPA-Net适用于宽高比范围内的图像。MPA-Net只使用图像,在训练和预测阶段不需要外部信息。因此,MPA-Net在美学评分预测以外的其他人类主观性预测方面具有很大的应用潜力。

英文摘要:

The spread of social networking services has created an increasing demand for selecting, editing, and generating impressive images. This trend increases the importance of evaluating image aesthetics as a complementary function of automatic image processing. We propose a multi-patch method, named MPA-Net (Multi-Patch Aggregation Network), to predict image aesthetics scores by maintaining the original aspect ratios of contents in the images. Through an experiment involving the large-scale AVA dataset, which contains 250,000 images, we show that the effectiveness of the equal-interval multi-patch selection approach for aesthetics score prediction is significant compared to the single-patch prediction and random patch selection approaches. For this dataset, MPA-Net outperforms the neural image assessment algorithm, which was regarded as a baseline method. In particular, MPA-Net yields a 0.073 (11.5%) higher linear correlation coefficient (LCC) of aesthetics scores and a 0.088 (14.4%) higher Spearman's rank correlation coefficient (SRCC). MPA-Net also reduces the mean square error (MSE) by 0.0115 (4.18%) and achieves results for the LCC and SRCC that are comparable to those of the state-of-the-art continuous aesthetics score prediction methods. Most notably, MPA-Net yields a significant lower MSE especially for images with aspect ratios far from 1.0, indicating that MPA-Net is useful for a wide range of image aspect ratios. MPA-Net uses only images and does not require external information during the training nor prediction stages. Therefore, MPA-Net has great potential for applications aside from aesthetics score prediction such as other human subjectivity prediction.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑