无需训练，单图生成风格化抽象图像，兼顾识别与艺术变形。
Training Free Stylized Abstraction
- 通过视觉语言模型在推理时提取身份特征，动态调整结构恢复策略。
- 多轮生成不需微调，支持多种抽象风格（如LEGO、South Park）且泛化性强。
- 提出新评估指标StyleBench，更符合人类对抽象图像的感知判断。
风格化抽象在保持语义忠实的同时，生成视觉夸张但可识别的图像表示。与强调结构保真的图像到图像转换不同，该任务需选择性保留身份线索并接受风格偏离，尤其对分布外个体更具挑战。本文提出一种无需训练的框架，仅用单张图像即可生成风格化抽象：利用视觉语言模型在推理阶段提取身份相关特征，并引入一种跨域校正流反演策略，基于风格依赖先验重建结构。通过风格感知的时间调度机制，动态调整结构修复过程，实现高保真还原，同时尊重主体与风格。支持无需微调的多轮抽象感知生成。为评估此任务，构建了基于GPT的人类对齐度量StyleBench，适用于像素级相似性失效的抽象风格场景。在多种抽象风格（如LEGO、针织娃娃、South Park）上的实验表明，方法在未见身份与风格上具备强泛化能力，整个系统完全开源。
原文摘要 · Abstract (English)
Stylized abstraction synthesizes visually exaggerated yet semantically faithful representations of subjects, balancing recognizability with perceptual distortion. Unlike image-to-image translation, which prioritizes structural fidelity, stylized abstraction demands selective retention of identity cues while embracing stylistic divergence, especially challenging for out-of-distribution individuals. We propose a training-free framework that generates stylized abstractions from a single image using inference-time scaling in vision-language models (VLLMs) to extract identity-relevant features, and a novel cross-domain rectified flow inversion strategy that reconstructs structure based on style-dependent priors. Our method adapts structural restoration dynamically through style-aware temporal scheduling, enabling high-fidelity reconstructions that honor both subject and style. It supports multi-round abstraction-aware generation without fine-tuning. To evaluate this task, we introduce StyleBench, a GPT-based human-aligned metric suited for abstract styles where pixel-level similarity fails. Experiments across diverse abstraction (e.g., LEGO, knitted dolls, South Park) show strong generalization to unseen identities and styles in a fully open-source setup.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。