发表机构
The University of Tokyo; RIKEN Center for Advanced Intelligence Project（东京大学; 理化学研究所先进智能项目中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出LF-MultiDiffusion，一种扩展MultiDiffusion的无训练球面全景生成方法，通过重新表述潜在聚合问题提升效率与质量，实现15.36倍加速且性能优于基线。
AI 中文摘要
我们提出了LF-MultiDiffusion，这是一种无训练的全景图生成方法，它扩展了MultiDiffusion以支持目标与参考图像空间之间的线性投影。我们的核心思路是将潜在聚合重新表述为正则化最小二乘问题，并在去噪循环内使用基于Krylov的迭代求解器高效求解。该表述比以往的无训练方法能实现更密集、更自然的映射，用少得多的透视视图即可生成更稳定的结果。因此，LF-MultiDiffusion减少了去噪过程中图像生成器的评估次数，显著提升了推理效率。实验表明，LF-MultiDiffusion在视觉质量、文本对齐和全景一致性方面优于最强的无训练基线，同时实现了15.36倍的加速。我们的项目页面可访问此https URL。
英文摘要
We propose LF-MultiDiffusion, a training-free panorama generation method that extends MultiDiffusion to support linear projections between target and reference image spaces. Our key idea is to reformulate latent aggregation as a regularized least-squares problem and solve it efficiently with a Krylov-based iterative solver inside the denoising loop. This formulation enables denser and more natural mappings than prior training-free methods, yielding more stable generation with far fewer perspective views. As a result, LF-MultiDiffusion reduces the number of image generator evaluations during denoising and significantly improves inference efficiency. Experiments show that LF-MultiDiffusion achieves better visual quality, text alignment, and panoramic consistency than the strongest training-free baseline, while providing a 15.36$\times$ speedup. Our project page is available at: https://ahykw.github.io/lfmd.
CommentsAccepted to ECCV 2026
