Dr. Nathan Jacobs is a Professor in the Computer Science & Engineering department at Washington University in St. Louis and Director of the Multimodal Vision Research Laboratory. His research focuses on computer vision, specializing in learning-based algorithms for processing large-scale image collections. His current work develops techniques for understanding the visual world from geotagged imagery, including images from social networks, outdoor webcams, and satellites. His research has been funded by NSF, NIH, DARPA, IARPA, NGA, ARL, AFRL, and Google.
He has graduated 14 PhD students, with 6 placed in tenure-track faculty positions and others at leading technology companies including Microsoft, Zillow, and Kitware. He has also mentored numerous MS students and undergraduates, many of whom have gone on to pursue advanced degrees or careers in industry.
See my lab's page for a complete listing of publications.
@inproceedings{gao2026trajectory,
spotlight = {true},
annotation = {generative,geoai,remote_sensing,motion,transportation},
author = {Gao, Tianyi and Lin, Jiayu and Beaulieu, Danielle and Jacobs, Nathan},
title = {Trajectory-aware Cross-view Geo-Localization with Sequential Observations},
booktitle = {European Conference on Computer Vision (ECCV)},
month = sep,
day = {10},
thumbnail = {/thumbnails/trajectory_crossview_geolocalization.svg},
pdf = {https://arxiv.org/pdf/2607.15491},
archiveprefix = {arXiv},
primaryclass = {cs.CV},
project = {https://humblegamer.github.io/trajloc/},
eprint = {2607.15491},
year = {2026}
}
@inproceedings{cher2026earth,
spotlight = {true},
annotation = {generative,geoai,remote_sensing},
author = {Cher, Dan and Iqbal, Hamza and Xing, Eric and Wei, Brian and Jacobs, Nathan},
title = {Tesselating The Earth},
booktitle = {European Conference on Computer Vision (ECCV)},
pdf = {https://arxiv.org/pdf/2606.27514},
archiveprefix = {arXiv},
primaryclass = {cs.CV},
eprint = {2606.27514},
code = {https://github.com/mvrl/TTE},
month = sep,
day = {10},
thumbnail = {/thumbnails/tessellating_earth_vectorsynth.jpg},
year = {2026}
}
@inproceedings{wei2026terraditomega,
spotlight = {true},
annotation = {generative,geoai,remote_sensing},
author = {Wei, Brian and Sastry, Srikumar and Cher, Dan and Xing, Eric and Jacobs, Nathan},
title = {{TerraDiT-$\Omega$}: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive},
booktitle = {European Conference on Computer Vision (ECCV)},
month = sep,
day = {10},
primaryclass = {cs.CV},
eprint = {2606.31029},
pdf = {https://arxiv.org/pdf/2606.31029},
year = {2026},
thumbnail = {/thumbnails/geodit_omega_spatial_primitives.svg}
}
@inproceedings{xiong2026unidrive,
spotlight = {true},
annotation = {generative,vlm,transportation},
author = {Xiong, Zhexiao and Ye, Xin and Yaman, Burhan and Cheng, Sheng and Lu, Yiren and Luo, Jingru and Jacobs, Nathan and Ren, Liu},
title = {{UniDrive-WM}: Unified Understanding, Planning and Generation World Model For Autonomous Driving},
archiveprefix = {arXiv},
booktitle = {European Conference on Computer Vision (ECCV)},
project = {https://unidrive-wm.github.io/UniDrive-WM/},
month = sep,
day = {10},
author+an = {7=highlight},
primaryclass = {cs.CV},
eprint = {2601.04453},
pdf = {https://arxiv.org/pdf/2601.04453},
thumbnail = {/thumbnails/unidrive_world_model_rollouts.jpg},
year = {2026}
}
@inproceedings{sastry2026prom3e,
annotation = {ecology,representation_learning,remote_sensing,audio},
title = {{ProM3E}: Probabilistic Masked MultiModal Embedding Model for Ecology},
author = {Sastry, Srikumar and Khanal, Subash and Dhakal, Aayush and Lin, Jiayu and Cher, Dan and Jarosz, Phoenix and Jacobs, Nathan},
author+an = {7=highlight},
project = {https://vishu26.github.io/prom3e/},
press = {https://engineering.washu.edu/news/2026/AI-model-looks-for-missing-pieces-to-puzzle.html},
press_title = {AI model looks for missing pieces to puzzle},
month = jun,
year = {2026},
code = {https://github.com/mvrl/proM3E},
pdf = {https://arxiv.org/pdf/2511.02946.pdf},
thumbnail = {/thumbnails/prom3e.svg},
spotlight = {true},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
eprint = {2511.02946},
archiveprefix = {arXiv},
primaryclass = {cs.CV}
}
@inproceedings{dhakal2026simlbr,
annotation = {representation_learning,generative},
spotlight = {true},
title = {{SimLBR}: Learning to Detect Fake Images by Learning to Detect Real Images},
author = {Dhakal, Aayush and Khanal, Subash and Sastry, Srikumar and Arndt, Jacob and Dias, Philipe Ambrozio and Lunga, Dalton and Jacobs, Nathan},
author+an = {7=highlight},
month = jun,
year = {2026},
code = {https://github.com/mvrl/SimLBR},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
eprint = {2602.20412},
thumbnail = {/thumbnails/simlbr.svg},
pdf = {https://arxiv.org/pdf/2602.20412},
archiveprefix = {arXiv},
primaryclass = {cs.CV}
}
@inproceedings{prue2026,
annotation = {remote_sensing,geoai,agriculture},
pdf = {https://arxiv.org/pdf/2603.27101},
thumbnail = {/thumbnails/prue_field_boundaries.png},
title = {{PRUE}: A Practical Recipe for Field Boundary Segmentation at Scale},
author = {Muhawenayo, Gedeon and Robinson, Caleb and Khanal, Subash and Fang, Zhanpei and Corley, Isaac and Wollam, Alexander and Gao, Tianyi and Strnad, Leonard and Avery, Ryan and Estes, Lyndon and Tárano, Ana M. and Jacobs, Nathan and Kerner, Hannah},
author+an = {12=highlight},
month = jun,
spotlight = {true},
year = {2026},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
press = {https://engineering.washu.edu/news/2026/Boundaries-of-agricultural-fields-worldwide-now-publicly-available.html},
press_title = {Boundaries of agricultural fields worldwide now publicly available}
}
@inproceedings{sarkar2026diffvas,
spotlight = {true},
title = {{DiffVAS}: Diffusion-Guided Visual Active Search in Partially Observable Environments},
author = {Sarkar, Anindya and Sastry, Srikumar and Pirinen, Aleksis and Jacobs, Nathan and Vorobeychik, Yevgeniy},
year = {2026},
month = may,
note = {(oral)},
booktitle = {International Conference on Autonomous Agents and Multiagent Systems (AAMAS)},
author+an = {4=highlight},
annotation = {rl,remote_sensing,geoai,generative},
eprint = {2605.15519},
pdf = {https://arxiv.org/pdf/2605.15519},
archiveprefix = {arXiv},
primaryclass = {cs.CV},
day = {25},
thumbnail = {/thumbnails/diffvas.jpg}
}
@inproceedings{cher2026vector,
spotlight = {true},
annotation = {generative,remote_sensing,geoai,representation_learning},
author = {Cher, Dan and Wei, Brian and Sastry, Srikumar and Jacobs, Nathan},
title = {{VectorSynth}: Fine-Grained Satellite Image Synthesis with Structured Semantics},
booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
author+an = {4=highlight},
primaryclass = {cs.CV},
thumbnail = {/thumbnails/vector_synth.jpg},
month = mar,
eprint = {2511.07744},
pdf = {https://openaccess.thecvf.com//content/WACV2026/papers/Cher_VectorSynth_Fine-Grained_Satellite_Image_Synthesis_with_Structured_Semantics_WACV_2026_paper.pdf},
archiveprefix = {arXiv},
year = {2026}
}
@inproceedings{qiao2025genstereo,
spotlight = {true},
annotation = {generative,geometric},
author = {Qiao, Feng and Xiong, Zhexiao and Xing, Eric and Jacobs, Nathan},
pdf = {https://arxiv.org/pdf/2503.12720},
title = {Towards Open-World Generation of Stereo Images and Unsupervised Matching},
booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
project = {https://qjizhi.github.io/genstereo/},
thumbnail = {/thumbnails/genstereo.jpg},
code = {https://github.com/Qjizhi/GenStereo},
linkedin = {https://www.linkedin.com/posts/jacobsn_new-paper-alert-genstereo-towards-activity-7311027987846438913-5DTA?utm_source=share&utm_medium=member_desktop&rcm=ACoAAACWgMUBbrOLvty2wxK6klz29_SYYIMtEis},
year = {2025},
day = {20},
month = oct,
archiveprefix = {arXiv},
primaryclass = {cs.CV},
eprint = {2503.12720}
}