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.
KAUST researchers used 3D mapping technology via remote control helicopter to survey and create detailed renderings of Jeddah's Al Balad, a UNESCO World Heritage Site. The team, from KAUST's Visual Computer Center and FalconViz, captured high-definition images from about 50 meters above street level. This enabled the creation of accurate 3D models, showing building shifts and potential problems for urban planners. Why it matters: This method provides a rapid and accurate way to document and preserve historical landmarks, especially in areas where traditional surveying is difficult or infeasible, aiding in cultural heritage preservation efforts.
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.
A researcher at the University of Oxford presented new findings on 3D neural reconstruction. The talk introduced a dataset comprising real-world video captures with perfect 3D models. A novel joint optimization method refines camera poses during the reconstruction process. Why it matters: High-quality 3D reconstruction has broad applicability to robotics and computer vision applications in the region.
Ian Reid, a Professor of Computer Science at the University of Adelaide, gave a talk at MBZUAI on leveraging deep learning to go beyond geometric SLAM. The talk covered using prior domain knowledge to improve map and shape estimation and enabling navigation in unvisited environments. The research aims to turn cameras into devices for flexible, large-scale situational awareness or "Spatial AI" sensors. Why it matters: Integrating deep learning with SLAM could significantly advance robotic navigation and spatial understanding, with applications for autonomous systems in various industries.
Dr. Xiaoming Liu from Michigan State University discussed computer vision techniques for 3D world understanding at a talk hosted by MBZUAI. The talk covered 3D reconstruction, detection, depth estimation, and velocity estimation, with applications in biometrics and autonomous driving. Dr. Liu also touched on anti-spoofing and fair face recognition research at MSU's Computer Vision Lab. Why it matters: Showcasing international experts and research directions helps to catalyze computer vision and 3D understanding research efforts within the UAE's AI ecosystem.
MBZUAI researchers have introduced SURPRISE3D, a benchmark for evaluating 3D spatial reasoning in AI systems, along with a 3D Spatial Reasoning Segmentation (3D-SRS) task. The benchmark includes over 900 indoor scenes and 200,000 language queries paired with 3D masks, emphasizing spatial relationships over object naming. A companion paper, MLLM-For3D, explores adapting 2D multimodal LLMs for 3D reasoning. Why it matters: This work addresses a key limitation in current AI, pushing towards embodied AI that can understand and act in 3D environments based on human-like spatial reasoning.