EmoKGEdit: 无训练情感注入 via 视觉线索转换
EmoKGEdit: Training-free Affective Injection via Visual Cue Transformation
AI总结：
EmoKGEdit通过构建多模态情感关联知识图谱，实现无训练的精确情感注入，有效分离情感属性与布局特征，提升图像情感编辑的保真度和结构一致性。
摘要：
现有图像情感编辑方法难以分离情感线索与潜在内容表示，往往导致弱的情感表达和扭曲的视觉结构。为弥合这一差距，我们提出了EmoKGEdit，一种新颖的无训练框架，用于精确且结构保持的图像情感编辑。具体而言，我们构建了一个多模态情感关联知识图谱（MSA-KG），以解构物体、场景、属性、视觉线索和情感之间的复杂关系。MSA-KG显式编码了物体-属性-情感之间的因果链，并作为外部知识支持链式推理，指导多模态大模型推断合理的情感相关视觉线索并生成连贯的指令。此外，基于MSA-KG，我们设计了一个解耦的结构-情感编辑模块，该模块在潜在空间中显式分离情感属性与布局特征，从而确保目标情感被有效注入，同时严格保持视觉空间一致性。大量实验表明，EmoKGEdit在情感保真度和内容保持方面均表现出色，并优于最先进的方法。
英文摘要：
Existing image emotion editing methods struggle to disentangle emotional cues from latent content representations, often yielding weak emotional expression and distorted visual structures. To bridge this gap, we propose EmoKGEdit, a novel training-free framework for precise and structure-preserving image emotion editing. Specifically, we construct a Multimodal Sentiment Association Knowledge Graph (MSA-KG) to disentangle the intricate relationships among objects, scenes, attributes, visual clues and emotion. MSA-KG explicitly encode the causal chain among object-attribute-emotion, and as external knowledge to support chain of thought reasoning, guiding the multimodal large model to infer plausible emotion-related visual cues and generate coherent instructions. In addition, based on MSA-KG, we design a disentangled structure-emotion editing module that explicitly separates emotional attributes from layout features within the latent space, which ensures that the target emotion is effectively injected while strictly maintaining visual spatial coherence. Extensive experiments demonstrate that EmoKGEdit achieves excellent performance in both emotion fidelity and content preservation, and outperforms the state-of-the-art methods.
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。
