让AI搭积木，比看一万张照片更懂空间
大模型看照片能认出猫、认出车，但你让它判断“这个杯子在桌子后面还是前面”、“从侧面看这个场景长什么样”，它经常懵。研究者发现一个反直觉的招：与其喂更多真实世界的3D标注数据(又贵又容易出错)，不如让AI玩“搭积木”——用1.5万个合成的积木堆叠问题训练它，涵盖从3D投影到2D、换视角、结构组合这些基础空间能力。结果，在合成数据上练出来的AI，反而在真实世界的空间任务上比用真实数据训练的更强。这像小孩学几何不是靠背题，而是靠玩积木搭出空间感。它不是你明天能用上的功能，但指向一个趋势：AI的空间智能，可能靠“虚拟幼儿园”而不是“海量真实照片”来启蒙。
📄 原文摘要(英文)
Large Vision-Language Models (LVLMs) have achieved strong performance on diverse visual tasks, yet their ability to reconstruct and reason about the 3D structure of the scene depicted in 2D images -- referred to as spatial intelligence -- remains limited. Existing approaches attempt to address this gap by using real-scene spatial question answering datasets that require dense geometric annotations. However, constructing such labels is costly, time-consuming, and often noisy due to reliance on external perception modules. In this work, we propose a novel paradigm inspired by human cognitive development: learning foundational spatial skills through structured block-manipulation tasks. We introduce SpatialBlock-15k, a synthetic dataset of 15,000 block-stacking problems covering 3D-to-2D projection, viewpoint transformation, and structural combination. The dataset further incorporates controlled color modulation as visual cues to encourage anchor-based reasoning in visually complex conditions. Experiments demonstrate that LVLMs trained on our dataset through either direct answering or reasoning-based prediction significantly outperform baselines and generalize to real-world spatial tasks, despite the dataset's synthetic and compact nature. Code and data are available at https://github.com/rsoohyun/SpatialBlock.