NeuralSVG：一种用于文本到矢量生成的隐式表示
NeuralSVG: An Implicit Representation for Text-to-Vector Generation
AI总结：
针对文本生成 SVG 中参数冗余与分层结构不足的问题，本文提出受 NeRF 启发的隐式神经表示 NeuralSVG，利用 SDS 优化和 dropout 正则化生成可编辑、可推理时控制的分层矢量图形。
摘要：
矢量图形在设计中至关重要，为艺术家提供了一种通用媒介，用于创建分辨率无关且高度可编辑的视觉内容。视觉语言模型和扩散模型的最新进展激发了人们对文本到矢量图形生成的兴趣。然而，现有方法往往受到输出参数过多的困扰，或将分层结构这一矢量图形的核心特征视为次要目标，从而削弱了其实用性。认识到分层 SVG 表示的重要性，我们提出了 NeuralSVG，这是一种用于根据文本提示生成矢量图形的隐式神经表示。受 Neural Radiance Fields（NeRF，神经辐射场）启发，NeuralSVG 将整个场景编码到一个小型 MLP 网络的权重中，并使用 Score Distillation Sampling（SDS，分数蒸馏采样）进行优化。为了在生成的 SVG 中促进分层结构，我们引入了一种基于 dropout 的正则化技术，以增强每个形状的独立含义。我们还证明，使用神经表示带来了推理时控制的额外优势，使用户能够基于用户提供的输入动态调整生成的 SVG，而所有这些只需一个学习到的表示即可完成。通过广泛的定性和定量评估，我们证明 NeuralSVG 在生成结构化且灵活的 SVG 方面优于现有方法。
英文摘要：
Vector graphics are essential in design, providing artists with a versatile medium for creating resolution-independent and highly editable visual content. Recent advancements in vision-language and diffusion models have fueled interest in text-to-vector graphics generation. However, existing approaches often suffer from over-parameterized outputs or treat the layered structure - a core feature of vector graphics - as a secondary goal, diminishing their practical use. Recognizing the importance of layered SVG representations, we propose NeuralSVG, an implicit neural representation for generating vector graphics from text prompts. Inspired by Neural Radiance Fields (NeRFs), NeuralSVG encodes the entire scene into the weights of a small MLP network, optimized using Score Distillation Sampling (SDS). To encourage a layered structure in the generated SVG, we introduce a dropout-based regularization technique that strengthens the standalone meaning of each shape. We additionally demonstrate that utilizing a neural representation provides an added benefit of inference-time control, enabling users to dynamically adapt the generated SVG based on user-provided inputs, all with a single learned representation. Through extensive qualitative and quantitative evaluations, we demonstrate that NeuralSVG outperforms existing methods in generating structured and flexible SVG.
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。
