AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation

Akio Hayakawa, Yusuke Mukuta, Tatsuya Harada

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace direct-sampling MultiDiffusion with linear-fusion least-squares aggregationSphereDiff-style training-free panorama · Panorama generationruntime: 32m 15s -> 2m 6sImproved
use LF-MultiDiffusion instead of SphereDiffFlux panorama generation · Panorama generationCLIP score: 27.65 -> 29.19Improved
use LSMR instead of PCG solver (ablation)LF-MultiDiffusion · Panorama generationQAlign: 3.04 -> 3.34Improved
increase solver iterations from 10 to 30 (ablation)LF-MultiDiffusion (LSMR) · Panorama generationQAlign: 3.27 -> 3.34Improved
increase solver iterations from 30 to 100 (ablation)LF-MultiDiffusion (LSMR) · Panorama generationQAlign: 3.34 -> 3.30Hurt
add Laplacian regularizer lambda=1e-4 (ablation)LF-MultiDiffusion · Panorama generationQAlign: 3.282 -> 3.341Improved
ridge vs Laplacian regularizer (ablation)LF-MultiDiffusion · Panorama generationQAlign: 3.340 vs 3.341No clear effect
increase views from 6 to 14 (ablation)LF-MultiDiffusion · Panorama generationDistortion: 3.98 -> 4.64Improved
increase views from 6 to 14 (ablation)LF-MultiDiffusion · Panorama generationQAlign: 3.549 -> 3.341Hurt
increase views from 14 to 26 (ablation)LF-MultiDiffusion · Panorama generationruntime: 2m 6s -> 3m 18sHurt
use backward instead of forward projection (ablation)LF-MultiDiffusion ERP · Panorama generationruntime: 4m 42s -> 2m 6sImproved
use spherical latent instead of ERP latent (ablation)LF-MultiDiffusion · Panorama generationAesthetic: 0.616 -> 0.631Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy