Multimodal Vision Research Laboratory @ WashU

university

https://mvrl.washu.edu

AI & ML interests

Computer Vision; Geospatial AI; Multimodal Learning; Vision-Language Models; Ecology; Remote Sensing

Recent Activity

brianwe1 published a dataset about 18 hours ago

MVRL/TerraDiT-data

brianwe1 published a model about 18 hours ago

brianwe1 updated a collection about 20 hours ago

View all activity

Papers

Trajectory-aware Cross-view Geo-localization with Sequential Observations

TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive

View all Papers

MVRL 's papers 7

Submitted by

Tianyi

Trajectory-aware Cross-view Geo-localization with Sequential Observations

MVRL

Multimodal Vision Research Laboratory @ WashU

Submitted by

Srikumar Sastry

TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive

MVRL

Multimodal Vision Research Laboratory @ WashU

Submitted by

Feng Qiao

Track2View: 4D-Consistent Camera-Controlled Video Generation via Paired 3D Point Tracks

MVRL

Multimodal Vision Research Laboratory @ WashU

Submitted by

Srikumar Sastry

Global and Local Entailment Learning for Natural World Imagery

MVRL

Multimodal Vision Research Laboratory @ WashU

Submitted by

Feng Qiao

GenStereo: Towards Open-World Generation of Stereo Images and Unsupervised Matching

MVRL

Multimodal Vision Research Laboratory @ WashU

RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings

MVRL

Multimodal Vision Research Laboratory @ WashU

TaxaBind: A Unified Embedding Space for Ecological Applications

MVRL

Multimodal Vision Research Laboratory @ WashU