Learning to Generate Poetic Chinese Landscape Painting with Calligraphy
This addresses the problem of creating integrated artistic works from poetry for applications in digital art and cultural preservation, representing an incremental advancement over single image-to-image methods.
The paper tackles generating poetic Chinese landscape paintings with calligraphy by introducing Polaca, a system that takes classic poetry as input and outputs artistic landscape paintings with calligraphy, using three modules for text-to-image generation, image-to-image calligraphy creation, and image fusion.
In this paper, we present a novel system (denoted as Polaca) to generate poetic Chinese landscape painting with calligraphy. Unlike previous single image-to-image painting generation, Polaca takes the classic poetry as input and outputs the artistic landscape painting image with the corresponding calligraphy. It is equipped with three different modules to complete the whole piece of landscape painting artwork: the first one is a text-to-image module to generate landscape painting image, the second one is an image-to-image module to generate stylistic calligraphy image, and the third one is an image fusion module to fuse the two images into a whole piece of aesthetic artwork.