Abstract Summary
•
This paper introduces a framework to enhance multi-modal large language models (MLLMs) with robust multi-frame spatial understanding for real-world applications like robotics by incorporating depth perception, visual correspondence, and dynamic perception.
•
The framework leverages the MultiSPA dataset, a large-scale collection of over 27 million samples covering diverse 3D and 4D scenes, and introduces a benchmark for comprehensive evaluation across various spatial tasks with uniform metrics.
Abstract
Multi-modal large language models (MLLMs) have rapidly advanced in visual tasks, yet their spatial understanding remains limited to single images, leaving them ill-suited for robotics and other real-world applications that require multi-frame reasoning. In this paper, we propose a framework to equip MLLMs with robust multi-frame spatial understanding by integrating depth perception, visual correspondence, and dynamic perception. Central to our approach is the MultiSPA dataset, a novel, large-scale collection of more than 27 million samples spanning diverse 3D and 4D scenes. Alongside MultiSPA, we introduce a comprehensive benchmark that tests a wide spectrum of spatial tasks under uniform metrics. Our resulting model, Multi-SpatialMLLM, achieves significant gains over baselines and proprietary systems, demonstrating scalable, generalizable multi-frame reasoning. We further observe multi-task benefits and early indications of emergent capabilities in challenging scenarios, and showcase how our model can serve as a multi-frame reward annotator for robotics.