EmoEdit: Evoking Emotions through Image Manipulation
Jingyuan Yang, Jiawei Feng, Weibin Luo, Dani Lischinski, Daniel Cohen-Or, Hui Huang

TL;DR
EmoEdit is a novel approach that modifies images to evoke specific emotions by integrating content changes, leveraging a large dataset and an emotion-aware adapter to outperform existing methods.
Contribution
We introduce EmoEdit, a new AIM framework with a large-scale dataset and an emotion adapter, enabling precise emotional image manipulation and transferability across models.
Findings
EmoEdit outperforms existing AIM methods in eliciting targeted emotions.
The Emotion adapter effectively makes generative models emotion-aware.
Our dataset EmoEditSet facilitates large-scale emotion attribution in images.
Abstract
Affective Image Manipulation (AIM) seeks to modify user-provided images to evoke specific emotional responses. This task is inherently complex due to its twofold objective: significantly evoking the intended emotion, while preserving the original image composition. Existing AIM methods primarily adjust color and style, often failing to elicit precise and profound emotional shifts. Drawing on psychological insights, we introduce EmoEdit, which extends AIM by incorporating content modifications to enhance emotional impact. Specifically, we first construct EmoEditSet, a large-scale AIM dataset comprising 40,120 paired data through emotion attribution and data construction. To make existing generative models emotion-aware, we design the Emotion adapter and train it using EmoEditSet. We further propose an instruction loss to capture the semantic variations in data pairs. Our method is…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis
MethodsAdapter
