SVGDreamer++:提升文本引导SVG生成的可编辑性与多样性
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation
AI总结:
针对现有文本转SVG方法可编辑性弱、视觉质量与多样性不足的问题,提出结合HIVE层级矢量化框架与VPSD粒子分数蒸馏的SVGDreamer++方法,辅以自适应基元控制与奖励模型,在多项指标上优于基线,支持多风格高质量矢量生成。
摘要:
近年来,文本引导的可缩放矢量图形(SVG)合成在图标设计、草图绘制等领域展现出巨大潜力。然而,现有文本转SVG方法生成的SVG往往缺乏可编辑性,且在视觉质量和多样性上存在不足。本文提出一种新型文本引导矢量图形合成方法以解决这些局限。为提升输出SVG的可编辑性,我们引入了层级图像矢量化(Hierarchical Image VEctorization, HIVE)框架,该框架在语义对象层面运行,并对矢量对象内部的组件优化进行监督,推动矢量图形解耦为独立的对象层级与组件层级。我们提出的HIVE算法结合图像分割先验,不仅能实现更精准的矢量图形表征,还支持矢量对象内部的细粒度编辑能力。为提升输出SVG的多样性,我们提出了基于矢量化粒子的分数蒸馏(Vectorized Particle-based Score Distillation, VPSD)方法。VPSD解决了现有方法中的过饱和问题,并提升了样本多样性。我们引入预训练奖励模型对矢量粒子进行重加权,既提升了视觉美感,又实现了更快的收敛速度。此外,我们设计了一种新型自适应矢量基元控制策略,可动态调整基元数量,从而增强图形细节的呈现效果。大量实验验证了所提方法的有效性,表明其在可编辑性、视觉质量和多样性方面均优于基线方法。我们还展示了该新方法支持多达6种不同的矢量风格,能够生成适用于风格化矢量设计和海报设计的高质量矢量素材。代码与演示将发布于:http://ximinng.github.io/SVGDreamerV2Project/
英文摘要:
Recently, text-guided scalable vector graphics (SVG) synthesis has demonstrated significant potential in domains such as iconography and sketching. However, SVGs generated from existing Text-to-SVG methods often lack editability and exhibit deficiencies in visual quality and diversity. In this paper, we propose a novel text-guided vector graphics synthesis method to address these limitations. To enhance the editability of output SVGs, we introduce a Hierarchical Image VEctorization (HIVE) framework that operates at the semantic object level and supervises the optimization of components within the vector object. This approach facilitates the decoupling of vector graphics into distinct objects and component levels. Our proposed HIVE algorithm, informed by image segmentation priors, not only ensures a more precise representation of vector graphics but also enables fine-grained editing capabilities within vector objects. To improve the diversity of output SVGs, we present a Vectorized Particle-based Score Distillation (VPSD) approach. VPSD addresses over-saturation issues in existing methods and enhances sample diversity. A pre-trained reward model is incorporated to re-weight vector particles, improving aesthetic appeal and enabling faster convergence. Additionally, we design a novel adaptive vector primitives control strategy, which allows for the dynamic adjustment of the number of primitives, thereby enhancing the presentation of graphic details. Extensive experiments validate the effectiveness of the proposed method, demonstrating its superiority over baseline methods in terms of editability, visual quality, and diversity. We also show that our new method supports up to six distinct vector styles, capable of generating high-quality vector assets suitable for stylized vector design and poster design. Code and demo will be released at: http://ximinng.github.io/SVGDreamerV2Project/
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。