Metraipolis › archive › dc_6be40316801b
Amplify What You Gaze At: Target Saliency Boosting in Text-to-Image Generation — arXiv:2609.30733
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30733
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T03:12:32.243Z
- SHA-256 of the archived text
f81132b21363e33b04cf6b2a765b01b8d9b1b1c368c90d572d0561bf23a47cd5- Stable URL of this page
https://metraipolis.com/documento/dc_6be40316801b
How to cite
Amplify What You Gaze At: Target Saliency Boosting in Text-to-Image Generation — arXiv:2609.30733 — arXiv (en), https://arxiv.org/abs/2609.30733 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6be40316801b (Metraipolis archive dc_6be40316801b, sha256 f81132b21363e33b04cf6b2a765b01b8d9b1b1c368c90d572d0561bf23a47cd5)
BibTeX
@misc{dc6be40316801b,
title = {Amplify What You Gaze At: Target Saliency Boosting in Text-to-Image Generation — arXiv:2609.30733},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30733},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6be40316801b; sha256 f81132b21363e33b04cf6b2a765b01b8d9b1b1c368c90d572d0561bf23a47cd5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30733. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Text-to-image generation has advanced in controlling what, where, and how objects appear, yet how visual attention is distributed among objects remains largely unexplored. In this paper, we introduce Target Saliency Boosting, a new task aimed at boosting the visual saliency of a specific object during text-to-image generation without requiring any visual priors. Our key insight is that visual saliency is inherently relative: boosting the saliency of a target object also depends on the global saliency distribution across all objects in the scene. Based on this insight, we propose GazeME, a lightweight framework that uses saliency-marked prompts, inserting learnable marker tokens around object descriptions to indicate which objects to visually emphasize or suppress. To learn these markers, we construct a saliency-semantics dataset that associates objects in image--prompt pairs with object-level saliency scores, and propose Saliency Prior Marker Activation (SPMA), a saliency-aware stochastic marker activation strategy that exploits relative saliency relationships for robust training. During inference, GazeME automatically inserts appropriate markers into the prompt, thereby directly enhancing the visual saliency of the target object. Extensive experiments demonstrate that GazeME effectively boosts target saliency while preserving both semantic alignment and image quality. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.30733 — 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 2026-10-08T02:50:19.041Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).