Text to image generation boosts focus on specific objects effectively
Amplify What You Gaze At: Target Saliency Boosting in Text-to-Image Generation
Computer Vision and Pattern Recognition
Summary
Text-to-image systems create pictures from written descriptions but often struggle to make specific objects stand out visually. The paper presents a new approach where the system learns to highlight a chosen object more clearly, without needing example images. The key idea is that making one object more noticeable depends on how other objects share attention. The authors built a method called GazeME that adds special markers in the text prompts to tell the system which objects to emphasize or downplay, improving how well the target object is seen without hurting picture quality.
What this means in practice
- •For graphic designers: Enhance text-to-image tools to make key elements in images more prominent when generating visuals from descriptions.
- •For advertising teams: Create marketing images where specific products or features automatically stand out more in AI-generated visuals.$Commercial implications: Enables selling AI-powered image generation services that emphasize advertised products more clearly to consumers.
Authors
Shengqi Dang, Zhengxi Yu, Feilin Han, Xingyu Lan, Nan Cao
Abstract
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.