SOURCE-LINKED INTELLIGENCE

Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

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 de

Read original source ↗ Open in workspace

recordType

paper

region

Global