6 papers
Chronosphere: Space-Time Tessellation of Local Climate Experts
Daniel Cher, Eric Xing, Kexing Li +3
We introduce Chronosphere, a spatio-temporal neural field that learns representations of climate. A central challenge in geographic representation learning is modeling environmenta…
Genesis: A Generative Engine for Hierarchical Satellite Image Synthesis
Subash Khanal, Yangzhi Cui, Daniel Cher +4
Earth observation is fundamentally multi-scale; geospatial tasks span varied resolutions, and satellite imagery is organized into cascading tile pyramids that nest fine detail with…
TerraDiT-: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive
Brian Wei, Srikumar Sastry, Daniel Cher +2
Generative models have achieved remarkable progress, yet applying them to satellite imagery remains challenging. Unlike natural imagery, satellite scenes are structured by spatiall…
Tessellating The Earth
Daniel Cher, Hamza Iqbal, Eric Xing +2
Geolocation encoders, which map geographic coordinates to learned representations, are emerging as an effective means of capturing visual and non-visual characteristics from a lati…
VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics
Daniel Cher, Brian Wei, Srikumar Sastry +1
We introduce VectorSynth, a diffusion-based framework for pixel-accurate satellite image synthesis conditioned on polygonal geographic annotations with semantic attributes. Unlike…
ProM3E: Probabilistic Masked MultiModal Embedding Model for Ecology
Srikumar Sastry, Subash Khanal, Aayush Dhakal +4
We introduce ProM3E, a probabilistic masked multimodal embedding model for any-to-any generation of multimodal representations for ecology. ProM3E is based on masked modality recon…