Geospatial Image Analysis is a rapidly developing field at the intersection of computer vision, machine learning, and geospatial imaging technologies. Images acquired from modern geospatial sensors (passive optical, such as multispectral and hyperspectral, as well as active sensing modalities such as LiDAR and Synthetic Aperture Radar) have the potential to support a wide array of applications, including environmental monitoring, climate science, urban modeling, disaster mitigation, etc. Although the potential of geospatial imagery to inform these applications is immense, there are unique challenges posed by the analysis of such imagery for scalable interpretation of geospatial imagery.  These include (but are not limited to) imagery representing a multitude of channels and scales depending on the sensor and the sensing platform (e.g. from drones to satellites), limited ground-truth, exploitation of heterogenous multi-modal imagery (e.g. combining passive optical imagery with Synthetic Aperture Radar and LiDAR measurements), significant domain differences caused by differences in sensors, seasons and/or imaging conditions, etc. 

This workshop will serve as a venue to foster collaborations and cross-fertilization of ideas between research groups in academia and the industry working in the areas of computer vision, machine learning, geospatial imaging and their applications to address pressing societal challenges. It will bring together leading researchers at the intersection of these areas working on both cutting-edge algorithmic approaches, and interesting and compelling applications of great societal interest. In addition to research contributions from the community, this workshop will also feature keynote talks from research leaders in industry and academia who are working at the forefront of computer vision for geospatial image analysis. 

 Call for Papers

We invite authors to submit high-quality papers on computer vision and image analysis for geospatial imaging. Submitted manuscripts will be peer-reviewed, and refereed for originality, presentation, empirical results and overall quality. In addition to papers focused on algorithmic novelty, we also encourage papers that demonstrate effective deployment of recent computer vision paradigms to compelling geospatial imaging applications. 

Topics of interest include (but are not limited to):

• Foundation models and large vision models in remote sensing

• Domain generalization and approaches to address out-of-distribution data, including open-set domain adaptation

• Agentic AI for spatial reasoning

• Self, Weakly and Unsupervised Approaches for Geospatial Image Analysis

• Uncertainty quantification and explainable machine learning in remote sensing

• Leveraging vision foundation models and multimodal foundation models for tasks such as semantic

• Segmentation, object detection, change and anomaly detection and image classification.

• Multimodal intelligent perception in remote sensing and Earth Observation.

• Applications including ecological monitoring, precision agriculture, sustainable development goals, disaster mapping etc.

Paper Format: We welcome the following types of papers:

• Regular research papers: We welcome regular/full research papers at the intersection of computer vision and geospatial imaging and its applications. These papers are limited to 8 pages (additional pages allowed for references) and will follow the WACV conference format. Authors should follow the Author Guidelines and use the WACV 2026 Author Kit available here. Accepted regular research papers that are presented at the workshop will be included in the WACV 2026 Workshop proceedings.

• Extended Abstracts: We also welcome extended abstracts that represent emerging and ongoing work at the intersection of computer vision and geospatial imaging and its applications. These must also be submitted through the same CMT system - Accepted abstracts will be presented at the workshop, but they will not be included in the workshop proceedings. 

All regular manuscripts will be peer-reviewed in a double-blind format, following the WACV format.

Manuscript Submission

Both regular papers and abstracts should be submitted via Microsoft CMT.
CMT Link for Paper Submission: https://cmt3.research.microsoft.com/GeoCV2026 

Organizers

Keynote Speakers

Important Dates

Regular Papers (archived in WACV Workshop Proceedings):
Deadline for Paper Submissions: November 30, 2025 December 20, 2025
Paper Decisions Announced: December 30, 2025
Camera Ready Paper Submission: January 9, 2026
Workshop Date: March 6, 2026

Extended Abstracts (not archived in WACV Workshop Proceedings):
Deadline for Extended Abstracts: January 9, 2026

Accepted Papers

We would like to congratulate the following papers on their acceptance to the Second Workshop on Computer Vision for Geospatial Image Analysis! 

• Unsupervised Spatially Aware Gaussian Mixture Model via Implicit Deep Priors - Herbert Rakotonirina, Theophile Lohier, and Julien Baptiste.      

• Multi-Receptive Field Ensemble with Cross Entropy Masking for Class Imbalance in Remote Sensing Change Detection - Humza Naveed, Xina Zeng, Mitch Bryson, and Nagita Mehrseresht.    

• GLACIA: Instance–Aware Positional Reasoning for Glacial Lake Segmentation via Multimodal Large Language Model - Lalit Maurya, Saurabh Kaushik,  and Beth Tellman.      

• RAVEN: A Rapid Agentic Vision Framework for Emergency Response in Vulnerable Settlements - Arkadip Maitra, Suvajit Patra, and Sumantro Mukherjee.      

• Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems - Niloufar Alipour Talemi, Julia Boone, and Fatemeh Afghah.      

• K-Vehicles: A Remote Sensing Dataset for Vehicle Detection in Aerial Imagery - Edmundo Casas, Leo Thomas Ramos, Cristian Romero, and Francklin Rivas-Echeverría.    

• Gradient-Based Active Learning for Geospatial Semantic Segmentation with Large Vision Models - Ryan Faulkenberry, and Saurabh Prasad.      

• Type-Aware Ranking of Urban Similarity from Aerial Imagery - Idan Kligvasser, Yotam Intrator, George Leifman, Yuval Desheh, Aviad Barzilao, Niv Efron, and Ehud Rivlin.                                                                         

• Bridging the Domain Gap in Agricultural Vision: Parameter-Efficient VLM Adaptation via Expert Descriptions - Deeksha Aggarwal, Yash Mittal, and Uttam Kumar.      

• Satellite-Based Detection of Looted Archaeological Sites Using Machine Learning - Girmaw Abebe Tadesse, Titien Bartette, Andrew Hassanali, Allen Kim, Chemla Jonathan, Andrew Zolli, Robinson Caleb, Inbal Becker-Reshef, and Juan Lavista Ferres.                                                                     

• Foundation Models for Phenotyping Segmentation of Wheat Stripe Rust Resistance from UAV Hyperspectral Images - Jie Deng, Tailai Chen, Chenyu Li, and Danfeng Hong.

• Point-to-dense supervision framework for SAM based remote sensing segmentation with prototype refinement and structure aware, confidence guided topology learning - Anisha Chakravorty, and Shounak Chakraborty.      

• The King(dom) is Naked: Lightweight Machine Learning for Hyperspectral Bare Soil Detection - Agata M. Wijata, Bogdan Ruszczak, Lukkasz Tulczyjew, Nicolas Longepe, and Jakub Nalepa.  

• Contrast then Confidence (C²): Contrastive Pretraining for Uncertainty-Aware Out-of-Distribution Detection in Satellite Imagery - Rawhatur Rabbi, Fabliha Afaf Sarwar, Md Farhadul Islam, Tashik Ahmed, Sidu Rudro, Mahfujur Rahman, Meem Arafat Manab, and Jannatun Noor Kukta.                                                                       

• On-the-Fly OVD Adaptation with FLAME: Few-shot Localization via Active Marginal-Samples Exploration - Yehonathan Refael, Amit Aides, Aviad Barzilai, George Leifman, Vered Silverman, Bolous Jaber, and Genady Beryozkin.                                                                         

• Segment Anything but Farms: Comparing Segmentation Paradigms for Rural UAV Captured Ultra-High-Resolution Imagery - Snehalraj Chug, Dharmendra Singh Chaudhary, Subash Sidgel, Shubham Thapa, Lalit BC, Ghimire Nishan, Bipendra Basnyat, and Nirmalya Roy.   

Workshop Program

Coming soon!

Program Committee

• Bianco Michael, Microsoft

• Amey Sunil Kulkarni, Worcester Polytechnic Institute

• Hongcheng Jiang, University of Missouri

• Nandini Saini, IIT Jodhpur

• Ryan Faulkenberry, University of Houston

• Sudipan Saha, Indian Institute of Technology Delhi

• Gabriele Moser, Università di Genova

• Shivam Pande, Ghent University

• Heng Fang, KTH Royal Institute of Technology

• Shirsha Bose, Technical University of Munich

• Samrat Mukherjee, Indian Institute of Technology Bombay

• Mainak Singha, University of Trento

• Emanuele Dalsasso, EPFL

• Md Aminur Hossain, Signal And Image Processing Area

• Ksenia Bittner, German Aerospace Center

• Moloud Abdar, Deakin University

Past Workshops: 

GeoCV @ WACV 2025: 

The program for the workshop is now available here, and the workshop proceedings are now available here: https://openaccess.thecvf.com/WACV2025_workshops/GeoCV