PaperScope
LIVE · 2026-09-03 05:40 UTC

Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation

Akio Hayakawa, Yusuke Mukuta, Tatsuya Harada

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.01997 v1
Category
Submitted
2026-09-02

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.

Comment: Accepted to ECCV 2026

arXiv abs page · PDF · same-day batch