EmoAgent: A Multi-Agent Framework for Diverse Affective Image Manipulation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908417123155968 |
|---|---|
| author | Mao, Qi Hu, Haobo He, Yujie Gao, Difei Chen, Haokun Jin, Libiao |
| author_facet | Mao, Qi Hu, Haobo He, Yujie Gao, Difei Chen, Haokun Jin, Libiao |
| contents | Affective Image Manipulation (AIM) aims to alter visual elements within an image to evoke specific emotional responses from viewers. However, existing AIM approaches rely on rigid \emph{one-to-one} mappings between emotions and visual cues, making them ill-suited for the inherently subjective and diverse ways in which humans perceive and express emotion.To address this, we introduce a novel task setting termed \emph{Diverse AIM (D-AIM)}, aiming to generate multiple visually distinct yet emotionally consistent image edits from a single source image and target emotion. We propose \emph{EmoAgent}, the first multi-agent framework tailored specifically for D-AIM. EmoAgent explicitly decomposes the manipulation process into three specialized phases executed by collaborative agents: a Planning Agent that generates diverse emotional editing strategies, an Editing Agent that precisely executes these strategies, and a Critic Agent that iteratively refines the results to ensure emotional accuracy. This collaborative design empowers EmoAgent to model \emph{one-to-many} emotion-to-visual mappings, enabling semantically diverse and emotionally faithful edits.Extensive quantitative and qualitative evaluations demonstrate that EmoAgent substantially outperforms state-of-the-art approaches in both emotional fidelity and semantic diversity, effectively generating multiple distinct visual edits that convey the same target emotion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11290 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EmoAgent: A Multi-Agent Framework for Diverse Affective Image Manipulation Mao, Qi Hu, Haobo He, Yujie Gao, Difei Chen, Haokun Jin, Libiao Computer Vision and Pattern Recognition Image and Video Processing Affective Image Manipulation (AIM) aims to alter visual elements within an image to evoke specific emotional responses from viewers. However, existing AIM approaches rely on rigid \emph{one-to-one} mappings between emotions and visual cues, making them ill-suited for the inherently subjective and diverse ways in which humans perceive and express emotion.To address this, we introduce a novel task setting termed \emph{Diverse AIM (D-AIM)}, aiming to generate multiple visually distinct yet emotionally consistent image edits from a single source image and target emotion. We propose \emph{EmoAgent}, the first multi-agent framework tailored specifically for D-AIM. EmoAgent explicitly decomposes the manipulation process into three specialized phases executed by collaborative agents: a Planning Agent that generates diverse emotional editing strategies, an Editing Agent that precisely executes these strategies, and a Critic Agent that iteratively refines the results to ensure emotional accuracy. This collaborative design empowers EmoAgent to model \emph{one-to-many} emotion-to-visual mappings, enabling semantically diverse and emotionally faithful edits.Extensive quantitative and qualitative evaluations demonstrate that EmoAgent substantially outperforms state-of-the-art approaches in both emotional fidelity and semantic diversity, effectively generating multiple distinct visual edits that convey the same target emotion. |
| title | EmoAgent: A Multi-Agent Framework for Diverse Affective Image Manipulation |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2503.11290 |