3D Computer Vision Researcher

GEOINT Symposium 2026. April 15, 2026 May 3-6, 2026 | aurora, colorado | Booth #2230. At the USGIF GEOINT Symposium 2026, the leading event for the geospatial intelligence community, Kitware will present its latest advancements in AI test and evaluation (T&E), computer vision, and interactive visualization. Its work supports national security missions by enabling organizations to better analyze complex data and make informed decisions with confidence. Kitware Inc. invite you to connect with its team at Booth #2230 and join its training sessions and lightning talks to see how its open source technologies and applied research are addressing today's most pressing GEOINT challenges. Advancing AI test & evaluation for geospatial applications. Kitware is advancing the development and deployment of AI systems through a strong focus on test and evaluation. Its approach spans the full lifecycle of AI, from data preparation and model development to rigorous evaluation and operational transition, ensuring systems are reliable, effective, and aligned with mission requirements. As part of this effort, Kitware Inc. is contributing to DARPA's In the Moment (ITM) program, where Kitware Inc. design AI systems that align with human decision-making processes in complex environments. By prioritizing transparency and alignment with human-defined criteria, these systems provide more interpretable and actionable outputs. For large-scale geospatial workflows, Kitware offers open source platforms such as GeoWATCH and RDWATCH, which enable users to train, evaluate, and deploy AI on satellite imagery through intuitive, web-based tools. These platforms are built to integrate into existing pipelines and support efficient analysis at scale. Kitware Inc. also emphasize responsible and explainable AI, recognizing its importance in operational settings. Its XAITK Toolkit helps users understand how models arrive at their decisions, providing tools for evaluation, visualization, and explanation that strengthen trust and improve human-machine collaboration. In addition, Kitware's 3D vision technologies, including its open source TeleSculptor platform, convert aerial imagery and video into detailed 3D models using structure-from-motion techniques. These capabilities support mapping, object detection, and situational awareness - even in environments where metadata is incomplete or unavailable. Kitware develops its technologies in close collaboration with government and industry partners, delivering open source solutions that emphasize transparency, interoperability, and long-term impact. Visit Booth #2230 to experience these capabilities firsthand and connect with its team. Kitware training sessions and lightning talks. Training Session | Monday, May 4 from 7:30-8:30 AM Presenter: Matt Leotta, Ph.D. Vision-Language Models (VLMs) let you find and segment objects in large imagery datasets just by describing them in natural language, avoiding the need for costly data labeling and retraining. This session explains how these models work and how they can be applied to geospatial tasks like object detection, segmentation, and even 3D analysis. Training Session | Tuesday, May 5 from 2:00 - 3:00 PM Presenter: Scott McCloskey, Ph.D. Event-Based Sensing (EBS) is a new imaging approach where sensors capture only changes in brightness instead of full frames, enabling extremely fast, efficient, and high-dynamic-range data collection. This session introduces how EBS works and how it can be used in geospatial applications like tracking fast-moving objects and identifying vehicles using AI-driven analysis. Training Session | Wednesday, May 6 from 7:30-8:30 AM Presenter: Arslan Basharat, Ph.D. This session explores how Large Language Models can be adapted and aligned to match the specialized reasoning of GEOINT analysts, improving their usefulness in real-world decision-making. It also demonstrates techniques like fine-tuning and prompt training, along with multimodal AI applications, to enhance geospatial analysis workflows. Few-shot Building Damage Assessment Lightning Talk | Monday, May 4th from 3:50-3:55 pm Authors/Presenters: Dennis Melamed, Trevor Stout, and Cameron Johnson AI-based damage assessment models perform well with large labeled datasets but struggle to adapt quickly to new disasters where labeled data is scarce. This work presents a label-efficient approach that uses pretraining to extract general features, enabling accurate damage classification with as few as 100 labeled samples. The result is faster, more scalable damage assessment with significantly reduced labeling effort, accelerating the delivery of actionable intelligence. Understanding Sensor-based Robustness of Object Detection Models for Overhead Imagery Lightning Talk | Monday, May 4th from 3:45-3:50 pm Author/Presenters: Anthony Hoogs, Ph.D. AI object detection models for overhead imagery often struggle when deployed under sensor conditions different from their training data. This work uses the Natural Robustness Toolkit (NRTK) to simulate varied sensor parameters and systematically evaluate how these changes impact model performance. The results provide insight into model sensitivity and robustness, helping guide better training, evaluation, and deployment strategies. Formal Guarantees of AI Model Robustness for GEOINT Applications Lightning Talk | Tuesday, May 5th from 3:05-3:10 pm Author/Presenter: Anthony Hoogs, Ph.D. MAGNET is an open source toolkit developed under DARPA's AIQ program to evaluate and improve the reliability and generalization of AI models in real-world deployments. It provides a flexible framework for testing models across text, image, and multimodal tasks using structured evaluations and performance prediction methods. The goal is to help identify model limitations before deployment, supporting more robust and trustworthy AI systems for applications like GEOINT. Label What Matters: Open-Vocabulary 3D Semantic Segmentation for GEOINT Lightning Talk | Tuesday, May 5th from 2:10-2:15 pm Author/Presenter: Matt Leotta, Ph.D 3D models from UAS and satellite imagery are valuable for GEOINT but lack semantic labels, limiting their usefulness. GU3SS addresses this by using vision-language models to enable open-vocabulary 3D segmentation, allowing analysts to define targets with simple text prompts. This flexible approach reduces retraining needs and improves adaptability across changing missions and environments. Computer vision and AI at Kitware. Kitware is a recognized leader in developing advanced artificial intelligence and computer vision solutions for mission-critical applications. Kitware Inc. build systems that enable organizations to analyze imagery, video, and multimodal data at scale, with a focus on performance, transparency, and real-world deployment. Its work spans a wide range of technical areas, including: * AI test and evaluation for geospatial and mission systems * Human-aligned AI and decision support * Responsible and trustworthy AI * Geospatial analytics, remote sensing, and 3D reconstruction * Object detection, classification, and tracking * Multimedia integrity and activity detection * Open source platforms for operational AI deployment Kitware Inc. bring deep expertise across the full AI lifecycle, from data curation and model development to evaluation and transition, ensuring systems are robust, reliable, and aligned with mission needs in complex environments. Working in close collaboration with government agencies, industry partners, and academic institutions, Kitware Inc. deliver solutions that support a wide range of operational domains. Its technologies are designed to adapt to evolving challenges and provide lasting value across diverse mission areas. Contact its team to learn more about how Kitware Inc. can partner with you.

Digital Pathology and AI Congress 2026. April 10, 2026 May 7-8, 2026 | Columbus, Ohio. Kitware is heading to Columbus, Ohio, on May 7-8 to exhibit at the Digital Pathology & AI Congress. This event brings together experts across pathology, artificial intelligence, and biomedical research to explore how digital technologies are transforming the study and diagnosis of disease. As AI and whole-slide imaging technologies continue to mature, the focus is shifting from innovation to implementation. Many organizations are no longer asking whether these technologies work, they are focused on applying them effectively within existing environments. The challenge lies in scaling solutions, connecting them with existing platforms, and ensuring consistent performance across complex systems. At this year's Congress, Kitware is focused on helping organizations address these challenges by turning AI models into scalable, production-ready systems. From prototype to production in Digital Pathology. Most teams can develop AI models. Far fewer can turn those models into systems that operate reliably at scale. Kitware partners with organizations to bridge the gap between research and deployment, helping teams move from early-stage development to production-ready systems. Kitware Inc. design and build high-performance systems that: * Integrate AI into existing platforms without requiring a full rebuild. * Scale to support large whole-slide imaging datasets. * Enable multi-user workflows and evolving system requirements. Digital pathology systems must also evolve as data volumes, users, and requirements grow. They need to integrate with existing tools while avoiding long-term technical constraints. Its approach enables organizations to: * Integrate AI/ML into existing products without rebuilding their platforms. * Optimize performance for large WSI datasets and multi-user environments. * Maintain control through open, extensible architectures. * Support long-term system evolution with ongoing technical leadership. Unlike rigid or closed platforms, its systems are designed to integrate with your existing infrastructure and evolve with your needs over time. If you're building a digital pathology platform, developing AI-driven applications, or scaling research workflows, Kitware can help you create end-to-end systems. From data ingestion and annotation to model deployment and visualization, designed for real-world use. Proven expertise in Digital Pathology. Effective implementation requires deep domain expertise in whole-slide imaging, AI pipelines, and digital pathology workflows. Kitware's work is grounded in proven platforms like HistomicsTK and extended through custom architectures designed for performance, scalability, and long-term product growth. Kitware Inc. also support reproducible, auditable workflows aligned with regulated research and clinical environments and work with organizations to meet specific validation and compliance requirements. Insights from its work. As organizations operationalize AI in digital pathology, several consistent challenges emerge, well beyond model development. The primary challenge is integration. Applying AI in practice requires managing large, complex datasets, supporting flexible deployment across environments, and building workflows that are both scalable and usable for researchers and clinicians. This is especially clear with the rise of foundation models. While they offer powerful capabilities for analyzing whole-slide images, their impact depends on how easily teams can evaluate and incorporate them into existing workflows. With the right tooling, teams can compare approaches, adapt models to their data, and move from experimentation to applied use. At the same time, the scale and complexity of pathology data continue to grow. Efficient access to whole-slide images, along with strong visualization and data management capabilities, is essential for maintaining performance and supporting growth. As collaboration expands, protecting patient privacy remains critical. Automated de-identification helps remove sensitive information from images and metadata, enabling secure data sharing while maintaining compliance and supporting ongoing research. Let's connect. Planning to attend the Digital Pathology & AI Congress? Visit Kitware at the event or reach out in advance to start the conversation. Whether you're exploring new capabilities or looking for a long-term technical partner, Kitware can help you move from prototype to production. Your data is safe with Kitware Inc.! Kitware Inc. do not sell personal information.

Exploring urban infrastructure risk with GeoDatalytics. April 10, 2026 Urban infrastructure systems, such as transportation networks, are increasingly vulnerable to extreme weather events, aging infrastructure, and growing urban demand. Understanding how these pressures affect interconnected systems is critical for cities and infrastructure operators working to improve resilience. GeoDatalytics is an open source platform developed through a collaboration between Kitware and Northeastern University to address these challenges. It enables teams to organize complex urban datasets, explore scenario-based analyses, and evaluate how disruptions impact infrastructure systems across a city. Through an integrated workflow that combines simulation and geospatial analytics, GeoDatalytics helps bring fragmented data together into a unified environment for analysis and decision-making. Challenges in urban infrastructure analysis. Urban infrastructure systems are highly interconnected, making it difficult to assess how disruptions in one area affect others. Events such as flooding can simultaneously impact transportation networks, accessibility, and emergency response. Infrastructure teams often work with fragmented datasets and limited tools for exploring "what-if" scenarios, making it challenging to fully understand system-wide impacts. Addressing these limitations requires a more integrated approach to data management, modeling, and visualization. GeoDatalytics for integrated infrastructure analysis. GeoDatalytics provides a structured environment for managing projects and datasets, allowing users to work with transportation, environmental, and other infrastructure data in a consistent and reproducible way. The platform supports interactive geospatial visualization, enabling users to explore infrastructure systems and better understand spatial relationships across a city. These capabilities are paired with scenario-based workflows that allow users to simulate disruptions and evaluate their impacts. In the webinar, Kitware Inc. demonstrate an AI-driven flood simulation that models how environmental conditions affect infrastructure systems. This simulation is combined with transportation network analysis to assess how flooding disrupts mobility and accessibility. By integrating these capabilities, GeoDatalytics provides insight into how disruptions propagate across systems, helping users better understand infrastructure risk. Perspectives from the GeoDatalytics development team provide insight into the platform's design goals, current capabilities, and ongoing development. As an open source project, GeoDatalytics continues to evolve with an emphasis on expanding analytics workflows and supporting additional infrastructure domains. Partnering with Kitware for urban infrastructure analytics. With deep expertise in open source software, geospatial analytics, and large-scale data systems, Kitware developed GeoDatalytics to make infrastructure analysis more accessible, flexible, and scalable. Whether you're integrating diverse urban datasets, modeling disruption scenarios, or analyzing system-wide impacts, GeoDatalytics provides the tools needed to support informed, data-driven decision-making. If you're interested in exploring how GeoDatalytics can support your infrastructure resilience and planning efforts, its team can provide technical guidance, collaboration opportunities, and real-world applications.