DCText: 通过分而治之策略实现视觉文本生成的调度注意力遮罩
DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy
AI总结：
DCText通过分而治之策略和注意力遮罩技术，实现高效视觉文本生成，提升长文本和多文本处理能力，同时保持图像质量和生成效率。
摘要：
尽管最近的文本到图像模型在高保真文本渲染方面取得了进展，但它们仍然在处理长文本或多文本时面临挑战，因为全局注意力被稀释了。我们提出DCText，一种无需训练的视觉文本生成方法，采用分而治之的策略，利用多模态扩散变换器可靠的短文本生成能力。我们的方法首先通过提取和分割目标文本来分解提示，然后将每个部分分配到指定区域。为了在各自区域内准确渲染每个段落同时保持整体图像一致性，我们引入了两种注意力遮罩——文本聚焦和上下文扩展——在去噪过程中依次应用。此外，局部噪声初始化进一步提高了文本准确性和区域对齐性，而无需增加计算成本。在单句和多句基准测试中，DCText在不牺牲图像质量的同时实现了最佳文本准确性和最低的生成延迟。
英文摘要：
Despite recent text-to-image models achieving highfidelity text rendering, they still struggle with long or multiple texts due to diluted global attention. We propose DCText, a training-free visual text generation method that adopts a divide-and-conquer strategy, leveraging the reliable short-text generation of Multi-Modal Diffusion Transformers. Our method first decomposes a prompt by extracting and dividing the target text, then assigns each to a designated region. To accurately render each segment within their regions while preserving overall image coherence, we introduce two attention masks - Text-Focus and Context-Expansion - applied sequentially during denoising. Additionally, Localized Noise Initialization further improves text accuracy and region alignment without increasing computational cost. Extensive experiments on single- and multisentence benchmarks show that DCText achieves the best text accuracy without compromising image quality while also delivering the lowest generation latency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
