EmoCtrl: Controllable Emotional Image Content Generation
By: Jingyuan Yang, Weibin Luo, Hui Huang
Potential Business Impact:
Creates pictures matching words and feelings.
An image conveys meaning through both its visual content and emotional tone, jointly shaping human perception. We introduce Controllable Emotional Image Content Generation (C-EICG), which aims to generate images that remain faithful to a given content description while expressing a target emotion. Existing text-to-image models ensure content consistency but lack emotional awareness, whereas emotion-driven models generate affective results at the cost of content distortion. To address this gap, we propose EmoCtrl, supported by a dataset annotated with content, emotion, and affective prompts, bridging abstract emotions to visual cues. EmoCtrl incorporates textual and visual emotion enhancement modules that enrich affective expression via descriptive semantics and perceptual cues. The learned emotion tokens exhibit complementary effects, as demonstrated through ablations and visualizations. Quantatitive and qualatitive experiments demonstrate that EmoCtrl achieves faithful content and expressive emotion control, outperforming existing methods across multiple aspects. User studies confirm EmoCtrl's strong alignment with human preference. Moreover, EmoCtrl generalizes well to creative applications, further demonstrating the robustness and adaptability of the learned emotion tokens.
Similar Papers
EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model
CV and Pattern Recognition
Creates pictures showing exact feelings from words.
CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation
CV and Pattern Recognition
Creates pictures that show feelings, not just objects.
Analyzing Image Beyond Visual Aspect: Image Emotion Classification via Multiple-Affective Captioning
CV and Pattern Recognition
Lets computers understand feelings in pictures.