Composition and Style Attributes Guided Image Aesthetic Assessment

TL;DR

This paper introduces a multi-network approach that combines semantic, style, and composition analysis to automatically predict the aesthetic quality of images, achieving effective results on benchmark datasets.

Contribution

It presents a novel multi-network architecture integrating semantic, style, and composition features for image aesthetic assessment, with an adaptive hypernetwork for parameter prediction.

Findings

Effective aesthetic prediction on three benchmark datasets

The network accurately predicts style, composition, and aesthetic scores

Ablation studies validate the contribution of each component

Abstract

The aesthetic quality of an image is defined as the measure or appreciation of the beauty of an image. Aesthetics is inherently a subjective property but there are certain factors that influence it such as, the semantic content of the image, the attributes describing the artistic aspect, the photographic setup used for the shot, etc. In this paper we propose a method for the automatic prediction of the aesthetics of an image that is based on the analysis of the semantic content, the artistic style and the composition of the image. The proposed network includes: a pre-trained network for semantic features extraction (the Backbone); a Multi Layer Perceptron (MLP) network that relies on the Backbone features for the prediction of image attributes (the AttributeNet); a self-adaptive Hypernetwork that exploits the attributes prior encoded into the embedding generated by the AttributeNet to predict the parameters of the target network dedicated to aesthetic estimation (the AestheticNet). Given an image, the proposed multi-network is able to predict: style and composition attributes, and aesthetic score distribution. Results on three benchmark datasets demonstrate the effectiveness of the proposed method, while the ablation study gives a better understanding of the proposed network.