An Abstract Painting Generation Method Based on Deep Generative Model
- PDF / 1,611,219 Bytes
- 12 Pages / 439.37 x 666.142 pts Page_size
- 39 Downloads / 213 Views
An Abstract Painting Generation Method Based on Deep Generative Model Mao Li1 · Jiancheng Lv1 · Jian Wang1 · Yongsheng Sang1
© Springer Science+Business Media, LLC, part of Springer Nature 2019
Abstract Computer technology provides new conditions and possibilities for art creation and research, and also expands the forms of artistic expression. Computer-created art has thus become one of the important forms of art. In this paper, we proposed a novel method of generating abstract paintings. We used the public painting dataset WikiArt and designed a K-Means algorithm that automatically finds the optimal K value to perform color segmentation on these images, and divide the picture into different color blocks. We proposed the concept of the collection of color block (CoCB), which records all color block information of the segmented image and serves as an intermediate vector for the generation of abstract painting. We extracted the CoCB as an empirical sample and used a learning model based on deep learning to automatically generate brand-new CoCBs. We then converted the CoCBs into an abstract painting, so that the generated abstract painting also followed certain aesthetic rules. Experiments showed that the resulting abstract painting have great visual impact, and some of them have been installed as decorations in public and private spaces, as well as art institutions. Also, some artists and designers have used the results in their work. Keywords Generative art · Depth generation model · Abstract painting CoCBs
1 Introduction Computer technology has broken through the limitations of traditional art forms and imagination, brought about new possibilities for artistic creation, and provided new space for the development of technology [1–3]. Nowadays, an artist’s manual work is no longer considered
B
Jiancheng Lv [email protected] Mao Li [email protected] Jian Wang [email protected] Yongsheng Sang [email protected]
1
Sichuan University, No.24 South Section 1, Yihuan Road, Chengdu, China
123
M. Li et al.
necessary in the field of contemporary art. At many of today’s contemporary art exhibitions, we are able to see works created by computer technology. It has become accepted that some processes or stages of artistic creation can be automated. Computers can also distil aesthetic principles int a rational and comprehensible form [4]. Moreover, more and more artists have begun to use computers as an aid to create artistic works. Art created by computers has generally failed to achieve realism. Therefore, computergenerated art has historically focused on the generation of abstract paintings. Abstract painting mainly employs pure painting languages such as points, lines, planes, and textures to express the creators’ emotions and ideas (Fig. 1). In fact, Abstract painting is both an important form of painting and a way of simplifying the representation of objects. There are many abstract paintings in significant international art exhibitions and auctions today.These features of abstract painting provide bo
Data Loading...
