Edinburgh & ESA build COP-GEN, a latent diffusion model that treats Earth observation as a distribution, not a single prediction
anselm · x · 2026-09-09
Researchers from Edinburgh and ESA present COP-GEN, a multimodal latent diffusion model addressing a flaw in Earth observation: most models are deterministic, mapping a DEM and land-cover map to a single "most likely" optical image. But the same terrain can plausibly look very different depending on cloud cover, season, soil moisture, and atmospheric scattering — the correct answer is a distribution, not one image.
COP-GEN is built to model that distribution of plausible outcomes rather than collapse it to its mean, and the authors argue this probabilistic shift matters far more than it sounds.
More from Multimodal
- Gradium launches Voice Design: prompt-to-voice generation, free in API and Studio — thisdudelikesAI · 2026-09-09
- SuperSplat browser viewer showcases stunning user-uploaded 3D Gaussian captures — willeastcott · 2026-09-09
- 5 ChatGPT Image Prompts That Turn Casual Photos Into Pro Shots (Face Preserved) — TawohAwa · 2026-09-09
- Sculpt Canvas Brings 10-Brush 3D Sculpting Inside ComfyUI Graphs — skbphy · 2026-09-09
- 'Generate for the Edit' Accepted to SIGGRAPH Asia 2026 Posters — ring_hyacinth · 2026-09-09
- 10 Hours, 21 Revisions, 1.3M Polygons: Artist Builds Vintage Gym in Blender via GPT-6 Astra — petewoodbridge · 2026-09-09