MADI：面向视觉编辑的掩码增强扩散与推理时扩展
MADI: Masking-Augmented Diffusion with Inference-Time Scaling for Visual Editing
AI总结：
本文提出MADI框架，通过掩码增强高斯扩散训练策略和基于暂停令牌的推理时扩展机制，显著提升扩散模型在视觉编辑中的可编辑性、组合性与可控性。
摘要：
尽管扩散模型在文本到图像生成中取得了显著成功，但它们在接地视觉编辑和组合控制方面的有效性仍然具有挑战性。受自监督学习和上下文生成建模进展的启发，我们提出了一系列简单而强大的设计选择，显著增强了扩散模型在结构化、可控生成和编辑方面的能力。我们引入了掩码增强扩散与推理时扩展（MADI），这是一个通过两项核心创新来提高扩散模型可编辑性、组合性和可控性的框架。首先，我们提出了掩码增强高斯扩散（MAgD），这是一种具有双重破坏过程的新型训练策略，它将标准去噪得分匹配与掩码重建相结合，通过掩码前向过程中的噪声输入来实现。MAgD鼓励模型学习具有判别性和组合性的视觉表示，从而实现局部化和结构感知的编辑。其次，我们引入了一种基于暂停令牌（Pause Tokens）的推理时容量扩展机制，暂停令牌作为插入提示中的特殊占位符，用于在推理时增加计算容量。我们的研究结果表明，在训练期间采用表达性强且密集的提示可以进一步提升性能，尤其是对于MAgD。总之，MADI中的这些贡献显著增强了扩散模型的可编辑性，为其集成到更通用的上下文生成扩散架构中铺平了道路。
英文摘要：
Despite the remarkable success of diffusion models in text-to-image generation, their effectiveness in grounded visual editing and compositional control remains challenging. Motivated by advances in self-supervised learning and in-context generative modeling, we propose a series of simple yet powerful design choices that significantly enhance diffusion model capacity for structured, controllable generation and editing. We introduce Masking-Augmented Diffusion with Inference-Time Scaling (MADI), a framework that improves the editability, compositionality and controllability of diffusion models through two core innovations. First, we introduce Masking-Augmented gaussian Diffusion (MAgD), a novel training strategy with dual corruption process which combines standard denoising score matching and masked reconstruction by masking noisy input from forward process. MAgD encourages the model to learn discriminative and compositional visual representations, thus enabling localized and structure-aware editing. Second, we introduce an inference-time capacity scaling mechanism based on Pause Tokens, which act as special placeholders inserted into the prompt for increasing computational capacity at inference time. Our findings show that adopting expressive and dense prompts during training further enhances performance, particularly for MAgD. Together, these contributions in MADI substantially enhance the editability of diffusion models, paving the way toward their integration into more general-purpose, in-context generative diffusion architectures.
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。
