基于语义差异指导的多领域图像翻译
Language-Grounded Multi-Domain Image Translation via Semantic Difference Guidance
AI总结：
LACE通过语义差异指导实现多领域图像翻译，结合全局语义与局部结构特征融合及多领域控制机制，提升视觉翻译的保真度和可控性。
摘要：
多领域图像到图像翻译需要将自然语言提示中表达的语义差异转化为相应的视觉转换，同时保持无关的结构和语义内容。现有方法难以维持结构完整性并提供细粒度、属性特定的控制，尤其是在涉及多个领域时。我们提出LACE（语言引导的属性可控翻译），基于两个组件：（1）一个GLIP-Adapter，将全局语义与局部结构特征融合以保持一致性，（2）一个多领域控制指导机制，将源和目标提示之间的语义差异显式地转化为每种属性的翻译向量，使语言语义与领域级别的视觉变化对齐。这些模块共同实现了具有独立强度调节的组合多领域控制。在CelebA(Dialog)和BDD100K上的实验表明，LACE实现了高视觉保真度、结构保持和可解释的领域特定控制，优于现有基线。这使LACE成为一种跨模态内容生成框架，连接语言语义和可控的视觉翻译。
英文摘要：
Multi-domain image-to-image translation re quires grounding semantic differences ex pressed in natural language prompts into corresponding visual transformations, while preserving unrelated structural and seman tic content. Existing methods struggle to maintain structural integrity and provide fine grained, attribute-specific control, especially when multiple domains are involved. We propose LACE (Language-grounded Attribute Controllable Translation), built on two compo nents: (1) a GLIP-Adapter that fuses global semantics with local structural features to pre serve consistency, and (2) a Multi-Domain Control Guidance mechanism that explicitly grounds the semantic delta between source and target prompts into per-attribute translation vec tors, aligning linguistic semantics with domain level visual changes. Together, these modules enable compositional multi-domain control with independent strength modulation for each attribute. Experiments on CelebA(Dialog) and BDD100K demonstrate that LACE achieves high visual fidelity, structural preservation, and interpretable domain-specific control, surpass ing prior baselines. This positions LACE as a cross-modal content generation framework bridging language semantics and controllable visual translation.
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。
