ECCV 2026 workshop
September 8-9, 2026
Malmö, Sweden
Malmö Arena + Malmömässan
CV4GOOD is an ECCV 2026 workshop bringing computer vision research face to face with frontline humanitarian practice in Malmö, Sweden. Born from a partnership between The Good AI Lab and Médecins Sans Frontières, it pairs researchers building vision and Earth-observation pipelines with practitioners who can say what works in the field, what fails, and what is missing.
Humanitarian AI · Earth observation · conflict monitoring · responsible AI
co-hosted by
The Good AI Lab× Médecins Sans Frontières
A workshop shaped jointly by frontline humanitarian practice and computer-vision research.
Humanitarian contexts make AI trade-offs impossible to ignore. Here, innovation cannot be judged by novelty alone.
When models shape operational decisions that affect millions, robustness, auditability, calibrated uncertainty, and workflow fit stop being nice-to-haves.
CV4GOOD is a half-day workshop that brings computer vision research face to face with frontline humanitarian practice. Born from a partnership between The Good AI Lab and Médecins Sans Frontières, it pairs researchers building vision and Earth-observation pipelines with practitioners who can say what works in the field, what fails, and what is missing.
The workshop addresses decision support in high-stakes settings: conflict, displacement, food insecurity. It focuses on the requirements real deployment imposes: robustness under domain shift, scarce and noisy labels, auditability, calibrated uncertainty, and integration into existing workflows.
We aim to surface a practitioner-informed research agenda and catalyze collaborations between the ECCV community and humanitarian organizations.
focus areas
what deployment asks of AI
Robustness under domain shift, scarce and noisy labels, auditability, calibrated uncertainty, and real workflow fit.
We are a non-profit AI research collective driven by curiosity and guided by responsibility. We are scientists, professors, engineers, researchers, and developers coming together from top universities, labs, and companies.
We are here because we're curious about what AI can be and should be. We explore AI's possibilities and strive to ensure its benefits can reach everyone.
thegoodailab.orgMédecins Sans Frontières is a humanitarian movement built on a simple but powerful belief: every person, everywhere, deserves care when crisis strikes. Founded in 1971, MSF brings medical assistance to people affected by war, epidemics, disasters, and exclusion from healthcare.
It is an independent international organization, guided not by politics or profit, but by medical ethics and humanity. Beyond treating patients, MSF also speaks out when people are suffering in silence.
msf.orgThe workshop will take place in person and be streamed online for remote participants. The first half grounds the audience in humanitarian needs and deployed systems; the second broadens to methods, governance, and open discussion.
Half-day · in person + streamed
duration
10 min
Pier Luigi Dovesi · The Good AI Lab
duration
25 min
Ann De Schutter · MSF
What MSF uses, what breaks, and what the research community should build next.
duration
35 min
Jamon Van Den Hoek & Corey Scher · Conflict Ecology Lab
Satellite imagery, radar-based damage assessment, and near-real-time monitoring in active conflict.
duration
25 min
Joseph Redmon · OlmoEarth, Ai2
From dual-use concerns to open EO infrastructure for non-profits and NGOs.
30 min
Coffee break
A pause before the methods and governance half
duration
25 min
Sara Beery · MIT
Distribution shift, scarce labels, and methods that hold up in the real world.
duration
25 min
Heidy Khlaaf · AI Now Institute
Grounding governance in concrete safety engineering practice.
duration
45 min
Closing Panel
Open discussion bridging humanitarian needs, computer-vision methods, and responsible deployment.
duration
5 min
The people grounding the workshop in frontline practice, deployed methods, and governance.
field · research · governance
The program mixes humanitarian practice, academia, industry research, and governance. Practitioner and safety voices carry equal weight with frontier computer-vision research.
Médecins Sans Frontières
Earth Observation (GIS) Manager at MSF Vienna, leading the team that provides EO insights to MSF's global operations.
Sets the needs-from-the-field framing.
Conflict Ecology Lab · Oregon State
Associate Professor and PI using satellite imagery and machine learning to study how conflict affects people and landscapes.
Methods taken into active conflict monitoring.
Conflict Ecology Lab · Oregon State
Researcher working on radar-based damage assessment and InSAR conflict monitoring through clouds and at night.
Near-real-time, city-scale mapping under pressure.
OlmoEarth · Allen Institute for AI
Part of the OlmoEarth team building open foundation models for earth observation designed for non-profits and NGOs.
A direct reckoning with dual-use concerns.
MIT EECS
Assistant Professor focused on generalizable, data-efficient methods for real-world environmental monitoring.
Distribution shift, scarce labels, and deployment constraints.
AI Now Institute
Chief AI Scientist focused on AI safety in defense and autonomous weapons, with a background in safety engineering.
Grounds the panel in concrete high-stakes auditing practice.
field requirements
The question is not whether computer vision can contribute to humanitarian action, but how to make it trustworthy enough for high-stakes decisions and how to govern dual-use risks responsibly.
Optical and SAR pipelines for conflict and disaster response.
Detection and monitoring of displacement camps from space.
Multispectral and temporal sensing for early warning under pressure.
Decision support where operational conditions are hardest and least forgiving.
Transferable representations, few-shot adaptation, and multimodal reasoning.
How to make AI trustworthy enough for decisions about lives and aid.
deployment constraints
CV4GOOD brings together researchers, practitioners, and organizers across academia, humanitarian work, and applied AI to shape a field-informed workshop from the ground up. These are the people making it happen.
Pier Luigi Dovesi
The Good AI Lab · AMD Silo AI
Matteo Poggi
University of Bologna
Federico Tombari
The Good AI Lab · Google · TU Munich
Philip Torr
University of Oxford
Ann De Schutter
Médecins Sans Frontières
Giorgos Tolias
The Good AI Lab · Czech Technical University in Prague
Noa Garcia
Osaka University
Bill Psomas
The Good AI Lab · Czech Technical University in Prague
Gianluca Villani
The Good AI Lab · Qualcomm
Theodoros Panagiotakopoulos
The Good AI Lab · King
Rafailia Vlachou
The Good AI Lab · SEB
Maria Rosaria Briglia
The Good AI Lab · Sapienza University of Rome
Mattia Segù
The Good AI Lab · Google
Carlo Rapisarda
The Good AI Lab · GeoGuessr