MARVEL: Raster Gray-Level Manga Vectorization via Primitive-Wise Deep Reinforcement Learning
- 29 August 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (4) , 2677-2693
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 gray-level 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—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.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62372027, 61976012)
This publication has 48 references indexed in Scilit:
- Towards Layer-wise Image Vectorization2022
- Im2Vec: Synthesizing Vector Graphics without Vector Supervision2021
- Exploiting Aliasing for Manga Restoration2021
- ArtCoder: An End-to-end Method for Generating Scanning-robust Stylized QR Codes2021
- Deep Vectorization of Technical Drawings2020
- Sketchformer: Transformer-Based Representation for Sketched Structure2020
- Multi-content GAN for Few-Shot Font Style Transfer2018
- Raster-to-Vector: Revisiting Floorplan Transformation2017
- SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks2017
- Deep Residual Learning for Image Recognition2016