arXiv cs.AI· Ren Ajiki, Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser, Ko Watanabe, Riku Takahashi, Andreas Dengel, Jinjia Zhou·· 12 小时前AI 评分29
PASTA：提示词感知的退火扩散采样，无需训练即可严格保留图像预留区域
PASTA: Prompt-Aware Annealed Diffusion Sampling
AI 导读
PASTA 是一个无需训练的扩散采样框架，通过对允许生成物体的区域选择性施加语义引导，在采样过程中强制满足预留区域约束。它基于共享隐变量轨迹，用掩码引导融合完整提示词与上下文提示词的引导，并以退火调度在去噪早期抑制语义泄漏、后期逐步恢复视觉一致性。实验显示 PASTA 在提升预留区域保真度的同时保持了整体图像真实感与感知一致性，论文已被 ICONIP2026 接收。
正文 · 原文
Abstract:While Diffusion models produce high-quality images, real-world visual design requires intentionally preserving clean regions for headlines, logos, or UI elements. Existing layout-aware text-to-image methods struggle to strictly preserve reserved regions, often introducing unwanted content that complicates downstream editing. Existing approaches either manipulate attention to displace content or suppress conditioning via noise-level interventions. However, these methods sacrifice visual coherence, producing flat regions or noticeable style inconsistencies between reserved and non-reserved areas. To address this limitation, we propose a Prompt-Aware Shared-Latent Training-Free Annealed Diffusion Sampling (PASTA), a training-free framework that enforces reserved-region constraints by selectively applying semantic guidance to object-allowed regions during sampling. PASTA operates on a shared latent trajectory, where full-prompt and context-prompt guidance are fused through mask-guided sampling. An annealed schedule suppresses semantic leakage during early denoising stages while gradually restoring visual consistency in later stages. Extensive experiments demonstrate that PASTA improves reserved-region fidelity while preserving overall image realism and perceptual consistency.
| Comments: | 15 pages, 4 figures, 2 tables. Accepted to ICONIP2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.32390 [cs.CV] |
| (or arXiv:2610.32390v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32390 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ren Ajiki [view email]
[v1]
Fri, 23 Oct 2026 09:16:22 UTC (20,455 KB)
来源：arXiv cs.AI · arxiv.org