AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas

Fabio Quattrini, Vittorio Pippi, Silvia Cascianelli, Rita Cucchiara

ECCV 2024 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 11 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
apply MAD in all U-Net blocks instead of never (ablation)MAD on LDM · 512x3072 panoramas, LDMI-LPIPS: 0.64 -> 0.53Improved
apply MAD only in the mid (bottleneck) block (ablation)MAD on LDM · 512x3072 panoramas, LDMFID: 34.51 -> 34.80No clear effect
apply MAD in all blocks instead of never (ablation)MAD on LDM · 512x3072 panoramas, LDMFID: 34.51 -> 61.76Hurt
increase number of MAD application steps tau from 0 to 15 (ablation)MAD on LDM · 512x3072 panoramas, LDMI-LPIPS: 0.64 -> 0.56Improved
increase tau from 15 to 50 (apply MAD at every step) (ablation)MAD on LDM · 512x3072 panoramas, LDMFID: 48.52 -> 98.01Hurt
combine MAD with attention scaling (Attn-S) (ablation)MAD on LDM · 512x3072 panoramas, LDM, standard promptsmCLIP: 32.03 -> 32.17No clear effect
use MAD instead of direct inference at 512x3072Stable Diffusion LDM · 512x3072 panoramas, standard promptsFID: 87.64 -> 48.52Improved
use MAD instead of direct inference with 1 LCM stepLCM · 512x3072 panoramas, LCM 1 stepFID: 67.54 -> 72.43Hurt
use MAD instead of direct inference with 2 LCM stepsLCM · 512x3072 panoramas, LCM 2 stepsFID: 49.98 -> 35.69Improved
use MAD instead of MultiDiffusion and SyncDiffusionpanorama generation · user study, 6 promptshuman preferenceImproved

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