Multimodal Vision Research Laboratory

Computer vision and AI for understanding the physical and natural world

We develop new methods that learn from satellite imagery, ground-level photos, sound, and text, and we build them into collaborations on agriculture, ecology, forests, air quality, natural hazards, and public health.

Recent News

Full archive →

Core Methods

AI for Impact

Much of our most consequential work happens within larger collaborative efforts, where we contribute AI methods and models.

Biodiversity

Shared embeddings across species photos, sound, satellite imagery, and taxonomy, including TaxaBind and related work.

Air quality

Global fine particulate matter estimation that combines deep learning with geophysical models.

Natural hazards

Landslide mapping from lidar and terrain analysis.

Public health

The built environment and health, with a focus on spatial equity.

Spotlight Publications

  1. Thumbnail for Tessellating the Earth: Learnable Spherical Voronoi Partitions for Location Encoding
    Cher D, Iqbal H, Xing E, Wei B, Jacobs N. 2026. Tessellating the Earth: Learnable Spherical Voronoi Partitions for Location Encoding. In: European Conference on Computer Vision (ECCV).
  2. Thumbnail for TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive
    Wei B, Sastry S, Cher D, Xing E, Jacobs N. 2026. TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive. In: European Conference on Computer Vision (ECCV).
  3. Thumbnail for UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving
    Xiong Z, Ye X, Yaman B, Cheng S, Lu Y, Luo J, Jacobs N, Ren L. 2026. UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving. In: European Conference on Computer Vision (ECCV).
  4. Thumbnail for Trajectory-aware Cross-view Geo-Localization with Sequential Observations
    Gao T, Lin J, Beaulieu D, Jacobs N. 2026. Trajectory-aware Cross-view Geo-Localization with Sequential Observations. In: European Conference on Computer Vision (ECCV).
  5. Thumbnail for ProM3E: Probabilistic Masked MultiModal Embedding Model for Ecology
    Sastry S, Khanal S, Dhakal A, Lin J, Cher D, Jarosz P, Jacobs N. 2026. ProM3E: Probabilistic Masked MultiModal Embedding Model for Ecology. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  6. Thumbnail for SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images
    Dhakal A, Khanal S, Sastry S, Arndt J, Dias PA, Lunga D, Jacobs N. 2026. SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
All Publications →

About Us

We are a computer vision and machine learning lab in the McKelvey School of Engineering at Washington University in St. Louis, led by Nathan Jacobs. Our research spans multimodal representation learning, geospatial foundation models, and generative modeling. We publish at CVPR, ICCV, ECCV, NeurIPS, and WACV, and we release code, models, and datasets. We welcome postdocs, students, research staff, and visitors—see our openings and FAQ page to learn more about joining the lab.