Metraipolis › archive › dc_178505feeea9

Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models — arXiv:2609.02502

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.02502
License (as archived): CC0-1.0
Archived: 2026-10-17T03:38:16.532Z
SHA-256 of the archived text: df046be8404fd9fe299e90e5c5ea9a337a3191ea1250f8e22a0406e1fab175a1
Stable URL of this page: https://metraipolis.com/documento/dc_178505feeea9

How to cite

Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models — arXiv:2609.02502 — arXiv (en), https://arxiv.org/abs/2609.02502 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_178505feeea9 (Metraipolis archive dc_178505feeea9, sha256 df046be8404fd9fe299e90e5c5ea9a337a3191ea1250f8e22a0406e1fab175a1)

BibTeX

@misc{dc178505feeea9,
  title = {Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models — arXiv:2609.02502},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02502},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_178505feeea9; sha256 df046be8404fd9fe299e90e5c5ea9a337a3191ea1250f8e22a0406e1fab175a1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02502. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-to-image (T2I) models have achieved remarkable success at faithfully rendering specified objects and attributes, yet their ability to produce visual metaphors, images that convey abstract ideas by combining elements from two distinct domains, remains largely unexamined. To bridge this gap, we introduce VMetaphor-Bench, the first benchmark for evaluating visual metaphor generation in T2I models. It comprises 1,500 visual metaphors curated from real-world creative imagery, organized into three levels and ten categories, with each sample paired with two prompts of differing specificity. For evaluation, we develop a hybrid framework within an MLLM-as-judge paradigm, combining a multiple-choice question (MCQ) based protocol of 9,594 questions across four levels of metaphorical fidelity with a dimension-based scoring protocol along three perceptual dimensions. Extensive evaluation of 11 representative T2I models reveals that even the strongest proprietary models struggle with compositional structuring and cross-domain mapping, key aspects of metaphorical expression, highlighting visual metaphor generation as an important frontier for future T2I research.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.02502 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T03:13:12.555Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).