Images Speak Volumes: User-Centric Assessment of Image Generation for Accessible Communication
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913531916451840 |
|---|---|
| author | Anschütz, Miriam Sylaj, Tringa Groh, Georg |
| author_facet | Anschütz, Miriam Sylaj, Tringa Groh, Georg |
| contents | Explanatory images play a pivotal role in accessible and easy-to-read (E2R) texts. However, the images available in online databases are not tailored toward the respective texts, and the creation of customized images is expensive. In this large-scale study, we investigated whether text-to-image generation models can close this gap by providing customizable images quickly and easily. We benchmarked seven, four open- and three closed-source, image generation models and provide an extensive evaluation of the resulting images. In addition, we performed a user study with people from the E2R target group to examine whether the images met their requirements. We find that some of the models show remarkable performance, but none of the models are ready to be used at a larger scale without human supervision. Our research is an important step toward facilitating the creation of accessible information for E2R creators and tailoring accessible images to the target group's needs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_03430 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Images Speak Volumes: User-Centric Assessment of Image Generation for Accessible Communication Anschütz, Miriam Sylaj, Tringa Groh, Georg Computer Vision and Pattern Recognition Computation and Language Explanatory images play a pivotal role in accessible and easy-to-read (E2R) texts. However, the images available in online databases are not tailored toward the respective texts, and the creation of customized images is expensive. In this large-scale study, we investigated whether text-to-image generation models can close this gap by providing customizable images quickly and easily. We benchmarked seven, four open- and three closed-source, image generation models and provide an extensive evaluation of the resulting images. In addition, we performed a user study with people from the E2R target group to examine whether the images met their requirements. We find that some of the models show remarkable performance, but none of the models are ready to be used at a larger scale without human supervision. Our research is an important step toward facilitating the creation of accessible information for E2R creators and tailoring accessible images to the target group's needs. |
| title | Images Speak Volumes: User-Centric Assessment of Image Generation for Accessible Communication |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2410.03430 |