Research map / Image generation / Super-resolution
Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis
Yutong He, Dingjie Wang, Nicholas Lai, William Zhang, Chenlin Meng, Marshall Burke, David B. Lobell, Stefano Ermon
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 |
|---|---|---|---|
| remove pixel synthesizer G_P (ablation) | EAD · Texas housing | LPIPS: 0.3985 -> 0.4482 | Hurt |
| replace deep feature mapper F with single linear layer (ablation) | EAD · Texas housing | LPIPS: 0.3985 -> 0.4845 | Hurt |
| replace deep feature mapper F with single 3x3 conv (ablation) | EAD · Texas housing | LPIPS: 0.3985 -> 0.4604 | Hurt |
| remove global encoder F_A (ablation) | EAD · Texas housing | LPIPS: 0.3985 -> 0.4340 | Hurt |
| remove neighborhood encoder and decoder (ablation) | EAD · Texas housing | LPIPS: 0.3985 -> 0.4418 | Hurt |
| add decoder F_D to EA64 (EAD) (ablation) | EA64 · Texas housing | SSIM: 0.5954 -> 0.5848 | Mixed |
| add decoder F_D to EA64 (EAD) (ablation) | EA64 · Texas housing | LPIPS: 0.4053 -> 0.3985 | Improved |
| add continuous time dimension to E (ablation) | EA64 · fMoW-Sentinel2 crop field | LPIPS: 0.5380 -> 0.5197 | Improved |
| reduce patch size from 64 to 32 (ablation) | EA · Texas housing | LPIPS: 0.4053 -> 0.4254 | Hurt |
| replace cGAN Fusion with EAD | image generation · Texas housing t'<t | SSIM: 0.4220 -> 0.5225 | Improved |
| replace cGAN Fusion with EAD | image generation · Texas housing t'>t | LPIPS: 0.3936 -> 0.3695 | Improved |
| replace cGAN Fusion with EAD for pool counting | human evaluation · Texas housing | r2 with mean count: -0.0707 -> 0.6158 | Improved |
Closest papers by meaning
- Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model (CVPR 2024 · similarity 0.86)
- Scale-aware Recognition in Satellite Images under Resource Constraints (ICLR 2025 · similarity 0.85)
- ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks (CVPR 2026 · similarity 0.85)
- DiffusionSat: A Generative Foundation Model for Satellite Imagery (ICLR 2024 · similarity 0.84)
- GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution (NeurIPS 2025 · similarity 0.84)
- See What We Cannot See: A Geo-guided Reasoning Benchmark for Object Counting under Adverse Earth Observation Conditions (CVPR 2026 · 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.
