Marc Pollefeys from ETH Zurich and Microsoft Spatial AI Lab will discuss building 3D environment representations for assisting humans and robots. The talk covers visual 3D mapping, localization, spatial data access, and navigation using geometry and learning-based methods. It also explores building rich 3D semantic representations for scene interaction via open vocabulary queries leveraging foundation models. Why it matters: Advancements in spatial AI and 3D scene understanding are critical for enabling more capable robots and AI assistants in various applications within the region.
KAUST Assistant Professor Paula Moraga has authored a new textbook, "Spatial Statistics for Data Science: Theory and Practice with R," based on her lectures. The book is available for free on her website and in hard copy through the publisher. Dr. Moraga's research focuses on developing statistical methods and computational tools for geospatial data analysis and health surveillance, with applications in reducing disease burden and identifying high-risk populations. Why it matters: The publication strengthens KAUST's research profile in spatial data science and offers valuable open-source resources for addressing critical challenges in public health and resource management within Saudi Arabia and the broader region.
MBZUAI researchers have developed GeoPixel, a new multimodal model for pixel grounding in remote sensing images. GeoPixel associates individual pixels with object categories, enabling detailed image analysis by linking language to objects at the pixel level. The model was trained on a new dataset and benchmark, outperforming existing systems in precision. Why it matters: This advancement enhances the utility of remote sensing data for critical applications like environmental management and disaster response by providing more granular and accurate image interpretation.
KAUST's Peter Wonka discusses the challenges and advancements in creating data-rich, three-dimensional maps for various applications. His team is working with Boeing on 3D modeling tools for aerospace design. KAUST-funded FalconViz uses UAV drones to create 3D maps of disaster areas for first responders. Why it matters: This highlights KAUST's contribution to cutting-edge 3D modeling and its practical applications in industries like aerospace and disaster response in the region.
MBZUAI, in partnership with IBM Research, is developing GeoChat+, a vision-language model (VLM) for multi-modal, temporal remote sensing image analysis. GeoChat+ builds on the previous GeoChat model, enhancing capabilities with multi-modal images from various Earth observation systems like Sentinel-1, Sentinel-2, Landsat, and high-resolution imagery. GeoChat+ will integrate data from multiple satellites at different times to detect environmental changes and analyze the impact on soil quality, air quality, and erosion. Why it matters: This advancement promises to revolutionize geographic data analysis, providing detailed reports for high-risk regions and aiding reforestation efforts.
Researchers at MBZUAI, IBM Research, and other institutions have developed EarthDial, a new vision-language model (VLM) specifically designed to process geospatial data from remote sensing technologies. EarthDial handles data in multiple modalities and resolutions, processing images captured at different times to observe environmental changes. The model outperformed others on over 40 tasks including image classification, object detection, and change detection. Why it matters: This unified model bridges the gap between generic VLMs and domain-specific models, enabling complex geospatial data analysis for applications like disaster assessment and climate monitoring in the region.
Researchers in Saudi Arabia have developed a deep learning framework for automated counting and geolocation of palm trees using aerial images. The system uses a Faster R-CNN model trained on a dataset of 10,000 palm tree instances collected in the Kharj region using DJI drones. Geolocation accuracy of 2.8m was achieved using geotagged metadata and photogrammetry techniques.
This paper introduces a deep vision-based framework for predicting coastal floods under climate change, addressing the challenges of limited training data and high-dimensional output. The framework employs and compares various deep learning models, including a custom compact CNN architecture, against geostatistical and traditional machine learning methods. A new synthetic dataset of flood inundation maps for Abu Dhabi's coast is also provided to benchmark future models.