MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learning

TL;DR

MARVEL introduces a deep reinforcement learning method that vectorizes raster manga images by decomposing them into primitive stroke sequences, achieving high accuracy and smaller file sizes compared to previous methods.

Contribution

This paper presents a novel primitive-wise DRL approach for manga vectorization, improving accuracy and efficiency over existing image-to-vector techniques.

Findings

Achieves state-of-the-art vectorization quality.

Reduces file sizes while maintaining visual fidelity.

Outperforms previous learning-based methods.

Abstract

Manga is a fashionable Japanese-style comic form that is composed of black-and-white strokes and is generally displayed as raster images on digital devices. Typical mangas have simple textures, wide lines, and few color gradients, which are vectorizable natures to enjoy the merits of vector graphics, e.g., adaptive resolutions and small file sizes. In this paper, we propose MARVEL (MAnga's Raster to VEctor Learning), a primitive-wise approach for vectorizing raster mangas by Deep Reinforcement Learning (DRL). Unlike previous learning-based methods which predict vector parameters for an entire image, MARVEL introduces a new perspective that regards an entire manga as a collection of basic primitives\textemdash stroke lines, and designs a DRL model to decompose the target image into a primitive sequence for achieving accurate vectorization. To improve vectorization accuracies and decrease file sizes, we further propose a stroke accuracy reward to predict accurate stroke lines, and a pruning mechanism to avoid generating erroneous and repeated strokes. Extensive subjective and objective experiments show that our MARVEL can generate impressive results and reaches the state-of-the-art level. Our code is open-source at: https://github.com/SwordHolderSH/Mang2Vec.