Aesthetic Language Guidance Generation of Images Using Attribute Comparison
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).
Cite
@article{arxiv.2208.04740,
title = {Aesthetic Language Guidance Generation of Images Using Attribute Comparison},
author = {Xin Jin and Qiang Deng and Jianwen Lv and Heng Huang and Hao Lou and Chaoen Xiao},
journal= {arXiv preprint arXiv:2208.04740},
year = {2022}
}
Comments
13 pages, 18 figures, on going research