Halftoning with Multi-Agent Deep Reinforcement Learning

TL;DR

This paper introduces HALFTONERS, a multi-agent deep reinforcement learning approach for digital halftoning that produces high-quality, blue-noise-like halftone images with a simpler training scheme.

Contribution

It proposes a novel multi-agent reinforcement learning framework with a shared policy and a new anisotropy suppressing loss for improved halftoning.

Findings

Produces high-quality halftones with blue-noise properties

Relatively fast compared to existing methods

Uses a shared policy with low-variance policy gradient

Abstract

Deep neural networks have recently succeeded in digital halftoning using vanilla convolutional layers with high parallelism. However, existing deep methods fail to generate halftones with a satisfying blue-noise property and require complex training schemes. In this paper, we propose a halftoning method based on multi-agent deep reinforcement learning, called HALFTONERS, which learns a shared policy to generate high-quality halftone images. Specifically, we view the decision of each binary pixel value as an action of a virtual agent, whose policy is trained by a low-variance policy gradient. Moreover, the blue-noise property is achieved by a novel anisotropy suppressing loss function. Experiments show that our halftoning method produces high-quality halftones while staying relatively fast.