Paper
Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation
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 · Authors: Akio Hayakawa, Yusuke Mukuta, Tatsuya Harada · Published 2026-09-02 · arXiv:2609.01997
- Published
- 2026-09-02
- Authors
- 3
- arXiv
- 2609.01997
- Category
- cs.CV
Abstract
arXiv:2609.01997
Akio Hayakawa, Yusuke Mukuta, Tatsuya Harada
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.