Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation

2026-09-01

AI Summary

本文提出LF-MultiDiffusion，一种无需训练的全景图生成方法，通过线性投影和高效求解器优化潜变量聚合，提高了生成质量和效率。

Abstract

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.

Problem

• panorama generation
• training-free
• linear projections
• latent aggregation
• inference efficiency

Innovation

• training-free
• linear projections
• regularized least-squares
• Krylov-based iterative solver
• panorama generation