Flow-Guided Controllable Line Drawing Generation

TL;DR

This paper introduces a novel AI-based framework for controllable artistic line drawing from photos, combining vector flow creation, feature fusion, and style control to produce high-quality, realistic character line art.

Contribution

It proposes a new architecture integrating vector flow, feature fusion, and controllable style parameters for improved line drawing generation from images.

Findings

Outperforms existing methods in high-resolution line drawing quality

Enables controllable variation in line style and details

Achieves perceptually realistic and coherent character line art

Abstract

In this paper, we investigate the problem of automatically controllable artistic character line drawing generation from photographs by proposing a Vector Flow Aware and Line Controllable Image-to-Image Translation architecture, which can be viewed as an appealing intersection between Artificial Intelligence and Arts. Specifically, we first present an Image-to-Flow network (I2FNet) to efficiently and robustly create the vector flow field in a learning-based manner, which can provide a direction guide for drawing lines. Then, we introduce our well-designed Double Flow Generator (DFG) framework to fuse features from learned vector flow and input image flow guaranteeing the spatial coherence of lines. Meanwhile, in order to allow for controllable character line drawing generation, we integrate a Line Control Matrix (LCM) into DFG and train a Line Control Regressor (LCR) to synthesize drawings with different styles by elaborately controlling the level of details, such as thickness, smoothness, and continuity, of lines. Finally, we design a Fourier Transformation Loss to further constrain the character line generation from the frequency domain view of the point. Quantitative and qualitative experiments demonstrate that our approach can obtain superior performance in producing high-resolution character line-drawing images with perceptually realistic characteristics.