AffectDelta: Beyond Emotion Labels for Image Editing

2026-09-02

AI Summary

本文提出AffectDelta，通过在八维情绪分布间转换来实现图像编辑，以更精确地调整图像所传达的情绪，同时保持原有场景的一致性。

Abstract

Emotion-driven image editing aims to evoke a specified target emotion by modifying emotion-relevant visual cues in a source image, while preserving the overall composition and semantic-structural coherence of the original scene. Existing scene-level editors typically specify the target with a single emotion category and often learn visual transformations from operation-level text instructions. A category collapses a mixed affective endpoint into one dominant label, while language cannot precisely quantify how coexisting emotions should increase, decrease, or remain stable. We introduce AffectDelta, a source-aware editor that treats editing as a transition between eight-dimensional emotion distributions. A frozen Emotion Distribution Predictor estimates the source state, and the signed source-to-target difference encodes the direction and magnitude of the requested transition. Within AffectDelta, an internal transition encoder and a source-aware diffusion backbone jointly translate this signal into context-dependent semantic and appearance changes. To train this formulation, we construct AffectPair-249K, comprising 248,841 source-target pairs with predicted eight-dimensional distributions and spanning both cross-category and within-category transitions. Experiments against six baselines, combining quantitative evaluation with qualitative comparisons, demonstrate improved affective alignment and content preservation, while ablations validate our design choices. Code and dataset will be made publicly available upon acceptance.

Problem

• emotion-driven image editing
• visual transformations
• emotion distribution
• affective alignment

Innovation

• Emotion Distribution
• Source-aware Editor
• Affective Alignment
• Eight-dimensional Emotion
• Context-dependent Changes