Image Composition Assessment with Saliency-augmented Multi-pattern Pooling
This addresses a specific gap in aesthetic assessment for image analysis, though it is incremental as it builds on existing aesthetic methods.
The paper tackled the lack of datasets and methods for image composition assessment by introducing the first dataset CADB with professional ratings and proposing SAMP-Net, which outperformed previous aesthetic assessment approaches.
Image composition assessment is crucial in aesthetic assessment, which aims to assess the overall composition quality of a given image. However, to the best of our knowledge, there is neither dataset nor method specifically proposed for this task. In this paper, we contribute the first composition assessment dataset CADB with composition scores for each image provided by multiple professional raters. Besides, we propose a composition assessment network SAMP-Net with a novel Saliency-Augmented Multi-pattern Pooling (SAMP) module, which analyses visual layout from the perspectives of multiple composition patterns. We also leverage composition-relevant attributes to further boost the performance, and extend Earth Mover's Distance (EMD) loss to weighted EMD loss to eliminate the content bias. The experimental results show that our SAMP-Net can perform more favorably than previous aesthetic assessment approaches.