Affective Image Editing: Shaping Emotional Factors via Text Descriptions
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_ | 1866914219493949440 |
|---|---|
| author | Zhang, Peixuan Weng, Shuchen Zhu, Chengxuan Tang, Binghao Jia, Zijian Li, Si Shi, Boxin |
| author_facet | Zhang, Peixuan Weng, Shuchen Zhu, Chengxuan Tang, Binghao Jia, Zijian Li, Si Shi, Boxin |
| contents | In daily life, images as common affective stimuli have widespread applications. Despite significant progress in text-driven image editing, there is limited work focusing on understanding users' emotional requests. In this paper, we introduce AIEdiT for Affective Image Editing using Text descriptions, which evokes specific emotions by adaptively shaping multiple emotional factors across the entire images. To represent universal emotional priors, we build the continuous emotional spectrum and extract nuanced emotional requests. To manipulate emotional factors, we design the emotional mapper to translate visually-abstract emotional requests to visually-concrete semantic representations. To ensure that editing results evoke specific emotions, we introduce an MLLM to supervise the model training. During inference, we strategically distort visual elements and subsequently shape corresponding emotional factors to edit images according to users' instructions. Additionally, we introduce a large-scale dataset that includes the emotion-aligned text and image pair set for training and evaluation. Extensive experiments demonstrate that AIEdiT achieves superior performance, effectively reflecting users' emotional requests. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18699 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Affective Image Editing: Shaping Emotional Factors via Text Descriptions Zhang, Peixuan Weng, Shuchen Zhu, Chengxuan Tang, Binghao Jia, Zijian Li, Si Shi, Boxin Computer Vision and Pattern Recognition In daily life, images as common affective stimuli have widespread applications. Despite significant progress in text-driven image editing, there is limited work focusing on understanding users' emotional requests. In this paper, we introduce AIEdiT for Affective Image Editing using Text descriptions, which evokes specific emotions by adaptively shaping multiple emotional factors across the entire images. To represent universal emotional priors, we build the continuous emotional spectrum and extract nuanced emotional requests. To manipulate emotional factors, we design the emotional mapper to translate visually-abstract emotional requests to visually-concrete semantic representations. To ensure that editing results evoke specific emotions, we introduce an MLLM to supervise the model training. During inference, we strategically distort visual elements and subsequently shape corresponding emotional factors to edit images according to users' instructions. Additionally, we introduce a large-scale dataset that includes the emotion-aligned text and image pair set for training and evaluation. Extensive experiments demonstrate that AIEdiT achieves superior performance, effectively reflecting users' emotional requests. |
| title | Affective Image Editing: Shaping Emotional Factors via Text Descriptions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.18699 |