AlignMorph：通过显式语义传输实现免调优扩散图像变形

中文摘要 AI 辅助

图像变形旨在两个输入图像之间产生平滑且语义一致的过渡。现有的基于扩散的变形方法要么需要昂贵的逐对优化，要么依赖隐式空间对齐，这在大布局差异下容易失败。为解决这些限制，我们提出了AlignMorph，一种新颖的免调优扩散框架，遵循“传输-去噪”原则。我们显式地将几何对齐与生成去噪解耦，以避免结构纠缠。我们的框架包含两个核心组件：（1）全局语义传输，通过熵最优传输和可靠性感知的潜在空间扭曲实现扩散兼容的语义对齐；（2）坐标对齐生成，使用对称双阶段注意力交接在去噪过程中保持一致的空间坐标。无需任何调优，AlignMorph有效消除重影，并在变形基准上实现优越的结构连贯性和时间平滑性。代码可在该HTTPS URL获取。

英文摘要

Image morphing aims to produce a smooth and semantically consistent transition between two input images. Existing diffusion-based morphing methods either require expensive per-pair optimization or rely on implicit spatial alignment, which easily fails under large layout discrepancies. To address these limitations, we propose AlignMorph, a novel tuning-free diffusion framework guided by the principle of transport-then-denoise. We explicitly decouple geometric alignment from generative denoising to avoid structural entanglement. Our framework consists of two core components. (1) Global Semantic Transport, which achieves diffusion-compatible semantic alignment via entropic optimal transport and reliability-aware latent warping; and (2) Coordinate-Aligned Generation, which uses a symmetric bi-phase attention handoff to maintain consistent spatial coordinates throughout denoising. Without any tuning, AlignMorph effectively eliminates ghosting and achieves superior structural coherence and temporal smoothness on morphing benchmarks. Code is available at https://github.com/51xOne/Alignmorph.

发表机构

• Huazhong University of Science and Technology（华中科技大学）
• Beijing Jiaotong University（北京交通大学）
• Beihang University（北京航空航天大学）
• Peking University（北京大学）

机构由 AI 辅助整理，请以论文原文为准。