# Theme-Aware Aesthetic Distribution Prediction With Full-Resolution Photographs

## TL;DR

This paper introduces a full-resolution aesthetic quality assessment method that preserves aesthetic features by combining image padding with region pooling, and incorporates theme information for improved predictions.

## Contribution

It proposes a novel theme-aware AQA model using RoM pooling and theme encoding to better capture aesthetic features without damaging image quality.

## Key findings

- Outperforms state-of-the-art AQA methods
- Effectively preserves aesthetic features in full-resolution images
- Utilizes theme information for more accurate aesthetic evaluation

## Abstract

Aesthetic quality assessment (AQA) is a challenging task due to complex aesthetic factors. Currently, it is common to conduct AQA using deep neural networks that require fixed-size inputs. Existing methods mainly transform images by resizing, cropping, and padding or employ adaptive pooling to alternately capture the aesthetic features from fixed-size inputs. However, these transformations potentially damage aesthetic features. To address this issue, we propose a simple but effective method to accomplish full-resolution image AQA by combining image padding with region of image (RoM) pooling. Padding turns inputs into the same size. RoM pooling pools image features and discards extra padded features to eliminate the side effects of padding. In addition, the image aspect ratios are encoded and fused with visual features to remedy the shape information loss of RoM pooling. Furthermore, we observe that the same image may receive different aesthetic evaluations under different themes, which we call theme criterion bias. Hence, a theme-aware model that uses theme information to guide model predictions is proposed. Finally, we design an attention-based feature fusion module to effectively utilize both the shape and theme information. Extensive experiments prove the effectiveness of the proposed method over state-of-the-art methods.