Aesthetic Language Guidance Generation of Images Using Attribute Comparison

TL;DR

This paper introduces a method called ALG that provides natural language guidance for improving images based on aesthetic attributes like color, lighting, and composition, tailored for landscape and portrait photos.

Contribution

It proposes a novel aesthetic language guidance framework divided into template-based and image-based methods, addressing landscape and portrait image differences.

Findings

Guides image enhancement through natural language descriptions of aesthetic attribute differences.

Differentiates guidance strategies for landscape and portrait images.

Demonstrates effective aesthetic improvement in images using the proposed guidance.

Abstract

With the vigorous development of mobile photography technology, major mobile phone manufacturers are scrambling to improve the shooting ability of equipments and the photo beautification algorithm of software. However, the improvement of intelligent equipments and algorithms cannot replace human subjective photography technology. In this paper, we propose the aesthetic language guidance of image (ALG). We divide ALG into ALG-T and ALG-I according to whether the guiding rules are based on photography templates or guidance images. Whether it is ALG-T or ALG-I, we guide photography from three attributes of color, lighting and composition of the images. The differences of the three attributes between the input images and the photography templates or the guidance images are described in natural language, which is aesthetic natural language guidance (ALG). Also, because of the differences in lighting and composition between landscape images and portrait images, we divide the input images into landscape images and portrait images. Both ALG-T and ALG-I conduct aesthetic language guidance respectively for the two types of input images (landscape images and portrait images).