静默助手：NoiseQuery作为目标驱动图像生成的隐式引导
The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation
AI总结：
本研究提出NoiseQuery方法，以对齐高斯噪声作为隐式引导优化扩散模型的噪声初始化，无需调优即可跨架构泛化，可构建兼容多模型的复用噪声库，在高层语义和低层视觉属性上均提升生成质量，且计算开销低。
摘要：
在本研究中，我们提出NoiseQuery这一新型方法，用于在多功能目标驱动文本到图像（T2I）生成中优化噪声初始化。具体而言，我们提出利用对齐的高斯噪声作为隐式引导，补充文本提示等用户定义的显式输入，以提升生成质量与可控性。与针对特定模型设计的现有噪声优化方法不同，我们的方法基于对扩散公式中通用有限步噪声调度器设计的基础研究，无需调优即可在不同的基于扩散的架构中实现更好的泛化性。这种模型无关的特性使我们能够构建一个可复用的噪声库，兼容多种T2I模型与增强技术，作为更高效生成的基础层。大量实验表明，NoiseQuery可实现细粒度控制，不仅在高层语义上，还在通常仅靠文本难以指定的低层视觉属性上带来显著性能提升，且能无缝集成到现有工作流中，计算开销极低。
英文摘要：
In this work, we introduce NoiseQuery as a novel method for enhanced noise initialization in versatile goal-driven text-to-image (T2I) generation. Specifically, we propose to leverage an aligned Gaussian noise as implicit guidance to complement explicit user-defined inputs, such as text prompts, for better generation quality and controllability. Unlike existing noise optimization methods designed for specific models, our approach is grounded in a fundamental examination of the generic finite-step noise scheduler design in diffusion formulation, allowing better generalization across different diffusion-based architectures in a tuning-free manner. This model-agnostic nature allows us to construct a reusable noise library compatible with multiple T2I models and enhancement techniques, serving as a foundational layer for more effective generation. Extensive experiments demonstrate that NoiseQuery enables fine-grained control and yields significant performance boosts not only over high-level semantics but also over low-level visual attributes, which are typically difficult to specify through text alone, with seamless integration into current workflows with minimal computational overhead.
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。
