EmoKGEdit: Training-free Affective Injection via Visual Cue Transformation

TL;DR

EmoKGEdit is a training-free framework that enables precise and structure-preserving image emotion editing by leveraging a knowledge graph to disentangle emotional cues from content.

Contribution

It introduces a novel knowledge graph and a disentangled editing module for emotion editing without training, improving fidelity and content preservation.

Findings

Outperforms state-of-the-art methods in emotion fidelity.

Maintains visual spatial coherence during editing.

Achieves high content preservation and emotional accuracy.

Abstract

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.