AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Sat2Flow: A Structure-Aware Diffusion Framework for Human Flow Generation from Satellite Imagery

Xiangxu Wang, Tianhong Zhao, Wei Tu, Bowen Zhang, Guanzhou Chen, Jinzhou Cao

AAAI 2026 · Image generation › Fast diffusion sampling · approach: Flow matching distillation · 4 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
add contrastive alignment of multi-kernel and OD latents (ablation)Sat2Flow · CommutingODGen test citiesRMSE: 76.00 -> 65.10Improved
use Pi-net (up-then-down) instead of standard U-net (ablation)Sat2Flow · CommutingODGen test citiesRMSE: 71.70 -> 65.10Improved
add topological distance prior to multi-kernel encoder (ablation)Sat2Flow · CommutingODGen test citiesRMSE: 65.60 -> 65.10No clear effect
use satellite imagery only instead of feature-rich inputsSat2Flow vs WeDAN · CommutingODGen test citiesCPC: 0.593 -> 0.635Improved
permutation-aware diffusion training under full index permutationSat2Flow vs DiffODGen · CommutingODGen (100% index permutation)JSD: 0.211 -> 0.171Improved
increase index permutation from 10% to 100% on matrix-wise baselinesDiffODGen · CommutingODGenJSD: 0.156 -> 0.211Hurt
increase index permutation from 10% to 100%Sat2Flow · CommutingODGenJSD: 0.149 -> 0.171Mixed

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