Neural-Polyptych: Content Controllable Painting Recreation for Diverse Genres

TL;DR

Neural-Polyptych is a unified GAN-based framework that enables content-controllable, high-resolution digital painting creation by integrating sketches with original artwork fragments, supporting diverse artistic styles and applications.

Contribution

It introduces a multi-scale GAN architecture with a novel Correspondence Attention module and Reference Bank strategy for detailed, global, and local feature integration in high-resolution painting generation.

Findings

Successfully generates megapixel-scale paintings across diverse genres.

Enables applications like large painting extension and genre switching.

Achieves high-fidelity, detailed artwork with global consistency.

Abstract

To bridge the gap between artists and non-specialists, we present a unified framework, Neural-Polyptych, to facilitate the creation of expansive, high-resolution paintings by seamlessly incorporating interactive hand-drawn sketches with fragments from original paintings. We have designed a multi-scale GAN-based architecture to decompose the generation process into two parts, each responsible for identifying global and local features. To enhance the fidelity of semantic details generated from users' sketched outlines, we introduce a Correspondence Attention module utilizing our Reference Bank strategy. This ensures the creation of high-quality, intricately detailed elements within the artwork. The final result is achieved by carefully blending these local elements while preserving coherent global consistency. Consequently, this methodology enables the production of digital paintings at megapixel scale, accommodating diverse artistic expressions and enabling users to recreate content in a controlled manner. We validate our approach to diverse genres of both Eastern and Western paintings. Applications such as large painting extension, texture shuffling, genre switching, mural art restoration, and recomposition can be successfully based on our framework.