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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add contrastive alignment of multi-kernel and OD latents (ablation) | Sat2Flow · CommutingODGen test cities | RMSE: 76.00 -> 65.10 | Improved |
| use Pi-net (up-then-down) instead of standard U-net (ablation) | Sat2Flow · CommutingODGen test cities | RMSE: 71.70 -> 65.10 | Improved |
| add topological distance prior to multi-kernel encoder (ablation) | Sat2Flow · CommutingODGen test cities | RMSE: 65.60 -> 65.10 | No clear effect |
| use satellite imagery only instead of feature-rich inputs | Sat2Flow vs WeDAN · CommutingODGen test cities | CPC: 0.593 -> 0.635 | Improved |
| permutation-aware diffusion training under full index permutation | Sat2Flow vs DiffODGen · CommutingODGen (100% index permutation) | JSD: 0.211 -> 0.171 | Improved |
| increase index permutation from 10% to 100% on matrix-wise baselines | DiffODGen · CommutingODGen | JSD: 0.156 -> 0.211 | Hurt |
| increase index permutation from 10% to 100% | Sat2Flow · CommutingODGen | JSD: 0.149 -> 0.171 | Mixed |
Closest papers by meaning
- Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities (NeurIPS 2025 · similarity 0.90)
- SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark (NeurIPS 2026 · similarity 0.86)
- Explainable Origin-Destination Crowd Flow Interpolation via Variational Multi-Modal Recurrent Graph Auto-Encoder (AAAI 2024 · similarity 0.86)
- Diffusion Transformers as Open-World Spatiotemporal Foundation Models (NeurIPS 2025 · similarity 0.84)
- BO4Mob: Bayesian Optimization Benchmarks for High-Dimensional Urban Mobility Problem (NeurIPS 2025 · similarity 0.84)
- Generating Origin-Destination Matrices in Neural Spatial Interaction Models (NeurIPS 2024 · similarity 0.84)
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.
