March 7, 2026 – Tucson, AZ
Join us for a Full Day program (8am – 5pm MST)! The workshop is open to all attendees registered for WACV (full conference or workshop/tutorial-only registrations). WACV registration Information can be found here
The 3rd Workshop on Computer Vision for Earth Observation (CV4EO) is conceived as a platform to foster application-oriented, multidisciplinary interactions between the computer vision community and experts from geoscience domains, across academia, non-profit organizations, Earth observation data providers, government agencies and other stakeholders leveraging AI, computer vision, and Earth observation technologies for decision-making in applications such as disaster response, national security, and environmental protection.
Call for Papers (CfP):
We invite two types of submissions:
- Full papers (up to 8 pages, including figures and tables) presenting mature, original research on computer vision for earth observation methods and applications. Submissions should follow WACV’s formatting and double-blind review guidelines, with accepted papers to appear in the WACV 2026 Workshop Proceedings.
- Short papers including position papers, abstracts on work-in-progress, industrial applications demos, or descriptions of workflows and best practices for CV4EO. Accepted short papers will be part of the lightning talks and poster sessions, but will not be in the Proceedings.
- Workshop takeaways and accepted short papers will be invited for compilation into an extended journal article submission to IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing (JSTARS).
Topics include, but are not limited to:
- Foundation models for Earth observation applications, including custom and general architectural design, self-supervised learning strategies, and approaches for reasoning on heterogeneous spatiotemporal data.
- Data fusion and multimodal learning: integration of diverse sensing modalities (e.g., optical RGB/multispectral, SAR, LiDAR), tokenization strategies to promote cross/joint modal learning.
- Agentic AI in remote sensing. Integration of LLMs with computer vision techniques for reasoning and querying of Earth observation applications.
- Emerging advances: quantum machine learning for Earth observation, diffusion models for remote sensing data synthesis etc.
- Practical computer vision and machine learning for low resource Earth observation applications. Energy-efficient/lightweight architectures including mixture-of-experts for Earth observation application workflows.
- Benchmarking and evaluation protocols for CV4EO models: uncertainty quantification, trustworthiness, generalization, explainability, and application-oriented workflows.
- Ethical considerations (bias, privacy, fairness, accountability, reproducibility) and open challenges, case studies, and end-user application perspectives.
- Visual query answering, object detection, semantic/instance segmentation, classification techniques for applications in humanitarian assistance, precision agriculture, sustainable development goals, environment/wildlife monitoring etc.
Important Dates:
-
Paper submission deadline: 30 Nov 2025 07 December 2025(Sun), AoE
- Notification to authors:
30 Dec 2025 (Mon) 04 Jan 2026 (Sun)
-
Camera-ready deadline (WACV format): Jan 09, 2026 11:59 PM PST
