StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis
To leverage LLMs for visual synthesis, traditional methods convert raster image information into discrete grid tokens through specialized visual modules, while disrupting the model's ability to capture the true semantic representation of visual scenes. This paper posits that an alternative representation of images, vector graphics, can effectively surmount this limitation by enabling a more natural and semantically coherent segmentation of the image information. Thus, we introduce StrokeNUWA, a pioneering work exploring a better visual representation ''stroke tokens'' on vector graphics, which is inherently visual semantics rich, naturally compatible with LLMs, and highly compressed. Equipped with stroke tokens, StrokeNUWA can significantly surpass traditional LLM-based and optimization-based methods across various metrics in the vector graphic generation task. Besides, StrokeNUWA achieves up to a 94x speedup in inference over the speed of prior methods with an exceptional SVG code compression ratio of 6.9%.
Code (0)
등록된 구현이 없습니다.
Tasks
Vector GraphicsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors
We introduce VectorPainter, a novel framework designed for reference-guided text-to-vector-graphics synthesis. Based on our observation that the style of strokes can be an important aspect to distinguish different artist…
Imitation LearningVector GraphicsLeveraging Large Language Models For Scalable Vector Graphics Processing: A Review
In recent years, rapid advances in computer vision have significantly improved the processing and generation of raster images. However, vector graphics, which is essential in digital design, due to its scalability and ea…
Vector GraphicsArtistic Portrait Drawing with Vector Strokes
In this paper, we present a method, VectorPD, for converting a given human face image into a vector portrait sketch. VectorPD supports different levels of abstraction by simply controlling the number of strokes. Since ve…
Vector GraphicsMARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learning
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 …
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1Vectorized Region Based Brush Strokes for Artistic Rendering
Creating a stroke-by-stroke evolution process of a visual artwork tries to bridge the emotional and educational gap between the finished static artwork and its creation process. Recent stroke-based painting systems focus…