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.
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.
Safran.AI and the Technology Innovation Institute (TII) intend to form a strategic alliance to develop a next-generation Agentic AI geospatial intelligence (GEOINT) platform. The platform will combine Safran.AI’s GEOINT expertise with TII’s expertise in Agentic AI and orchestration platforms, enabling autonomous reasoning and transforming spaceborne imagery into decision-grade intelligence. The collaboration will focus on three major technological streams. Why it matters: This partnership signifies a major advancement in sovereign geospatial intelligence capabilities within the UAE, moving from traditional analysis to autonomous understanding for enhanced national security and decision-making.