Spatial Mental Modeling from Limited Views
This addresses a critical gap in VLMs' ability to reason about unseen space, which is important for applications requiring spatial understanding, but it is incremental as it builds on existing VLM methods with specific enhancements.
The paper tackles the problem of Vision Language Models (VLMs) struggling to form spatial mental models from limited views, as shown by near-random performance on the new MindCube benchmark, and achieves a significant improvement by using a 'map-then-reason' approach that boosts accuracy from 37.8% to 60.8% and further to 70.7% with reinforcement learning.
Can Vision Language Models (VLMs) imagine the full scene from just a few views, like humans do? Humans form spatial mental models, internal representations of unseen space, to reason about layout, perspective, and motion. Our new MindCube benchmark with 21,154 questions across 3,268 images exposes this critical gap, where existing VLMs exhibit near-random performance. Using MindCube, we systematically evaluate how well VLMs build robust spatial mental models through representing positions (cognitive mapping), orientations (perspective-taking), and dynamics (mental simulation for "what-if" movements). We then explore three approaches to help VLMs approximate spatial mental models, including unseen intermediate views, natural language reasoning chains, and cognitive maps. The significant improvement comes from a synergistic approach, "map-then-reason", that jointly trains the model to first generate a cognitive map and then reason upon it. By training models to reason over these internal maps, we boosted accuracy from 37.8% to 60.8% (+23.0%). Adding reinforcement learning pushed performance even further to 70.7% (+32.9%). Our key insight is that such scaffolding of spatial mental models, actively constructing and utilizing internal structured spatial representations with flexible reasoning processes, significantly improves understanding of unobservable space.