Hosting models for https://arxiv.org/abs/2505.21647
AI & ML interests
Computer Vision; Remote Sensing; Geospatial AI; Multimodal Learning; Vision-Language Models; Ecology; Foundation Models
Recent Activity
Papers
TerraDiT-$Ω$: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive
Track2View: 4D-Consistent Camera-Controlled Video Generation via Paired 3D Point Tracks
Organization Card
Multimodal Vision Research Laboratory
MVRL develops multimodal AI systems for remote sensing, ecology, geospatial reasoning, and vision-language understanding. This Hugging Face organization hosts models, datasets, and demos from our published research. For papers, code, and project pages, visit https://mvrl.cse.wustl.edu/.
models 59
MVRL/TTE
Feature Extraction • 3.45M • Updated • 37
MVRL/sat2sound
Updated
MVRL/VectorSynth-GiT10M
Image-to-Image • 0.9B • Updated • 1
MVRL/ProM3E
27.3M • Updated • 9
MVRL/presto_default_model
823k • Updated • 1
MVRL/dinov3-vitl16-pretrain-sat493m
0.3B • Updated • 30 • 1
MVRL/VectorSynth-COSA
Image-to-Image • 0.9B • Updated • 8
MVRL/VectorSynth
Image-to-Image • 0.9B • Updated • 33
MVRL/super-geo
9.45M • Updated • 4
MVRL/dinov3_vitl16_sat
Updated • 1
datasets 15
MVRL/SeqGeo-VL
Viewer • Updated • 38.9k • 66 • 2
MVRL/WebMix-38M
Viewer • Updated • 38.8M • 5.4k
MVRL/GeoSound
Preview • Updated • 89
MVRL/PlantTrait
Viewer • Updated • 307k • 24
MVRL/SoundingEarth
Viewer • Updated • 49.3k • 537
MVRL/MultiNat
Viewer • Updated • 83.7k • 48
MVRL/Geo-Embeddings-Dataset
Viewer • Updated • 1.86M • 55
MVRL/iNat-2021-train
Viewer • Updated • 2.69M • 213
MVRL/iNat-2021-val
Viewer • Updated • 100k • 73
MVRL/RANGE-database
Updated • 177 • 2