🤖 AI Summary
This work addresses the challenge of efficiently generating semantically coherent layouts for poster design that adhere to user-specified constraints. The authors propose an interactive layout generation framework that innovatively integrates a graph-augmented diffusion model with a content-aware attention mechanism. During the denoising process, a mask-based constraint-preserving strategy is introduced to maintain partial user intent—such as designated element categories, sizes, positions, or sketch inputs—while producing context-sensitive and visually coherent high-quality layouts. Experimental results demonstrate that the proposed method achieves state-of-the-art performance across multiple evaluation metrics and enables a real-time, highly controllable interactive design experience.
📝 Abstract
We present iPoster, an interactive layout generation framework that empowers users to guide content-aware poster layout design by specifying flexible constraints. iPoster enables users to specify partial intentions within the intention module, such as element categories, sizes, positions, or coarse initial drafts. Then, the generation module instantly generates refined, context-sensitive layouts that faithfully respect these constraints. iPoster employs a unified graph-enhanced diffusion architecture that supports various design tasks under user-specified constraints. These constraints are enforced through masking strategies that precisely preserve user input at every denoising step. A cross content-aware attention module aligns generated elements with salient regions of the canvas, ensuring visual coherence. Extensive experiments show that iPoster not only achieves state-of-the-art layout quality, but offers a responsive and controllable framework for poster layout design with constraints.