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

arXiv: https://arxiv.org/abs/2110.04830 · HTML: https://mlsanity.com/paper/2110.04830/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 62 references that are in the map.
- First posted on arXiv 10 Oct 2021.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation](https://mlsanity.com/paper/2007.11301/) (2020)
- [Im2Vec: Synthesizing Vector Graphics without Vector Supervision](https://mlsanity.com/paper/2102.02798/) (2021)
- [Multi-Content GAN for Few-Shot Font Style Transfer](https://mlsanity.com/paper/1712.00516/) (2017)
- [A Learned Representation for Scalable Vector Graphics](https://mlsanity.com/paper/1904.02632/) (2019)
- [Multimodal Transformer with Multi-View Visual Representation for Image Captioning](https://mlsanity.com/paper/1905.07841/) (2019)
- [Sketchformer: Transformer-based Representation for Sketched Structure](https://mlsanity.com/paper/2002.10381/) (2020)
- [Learning to Paint With Model-based Deep Reinforcement Learning](https://mlsanity.com/paper/1903.04411/) (2019)
- [Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning](https://mlsanity.com/paper/1910.04987/) (2019)
- [SurfNet: Generating 3D shape surfaces using deep residual networks](https://mlsanity.com/paper/1703.04079/) (2017)
- [Deep Vectorization of Technical Drawings](https://mlsanity.com/paper/2003.05471/) (2020)
- [Vectorization of Line Drawings via PolyVector Fields](https://mlsanity.com/paper/1801.01922/) (2018)
- [MangaGAN: Unpaired Photo-to-Manga Translation Based on The Methodology of Manga Drawing](https://mlsanity.com/paper/2004.10634/) (2020)
- [Exploiting Aliasing for Manga Restoration](https://mlsanity.com/paper/2105.06830/) (2021)
- [DeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfaces](https://mlsanity.com/paper/1901.03781/) (2019)
- [Deep Model-Based Reinforcement Learning for High-Dimensional Problems, a Survey](https://mlsanity.com/paper/2008.05598/) (2020)
- [Deeply Supervised Depth Map Super-Resolution as Novel View Synthesis](https://mlsanity.com/paper/1808.08688/) (2018)
- [Bilinear Supervised Hashing Based on 2D Image Features](https://mlsanity.com/paper/1901.01474/) (2019)

## Built on by (most cited first, 2 of 2)

- [LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization](https://mlsanity.com/paper/2505.23740/) (2025)
- [BG-Triangle: B'ezier Gaussian Triangle for 3D Vectorization and Rendering](https://mlsanity.com/paper/2503.13961/) (2025)

## Abstract (arXiv)

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 primitivestextemdash 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.