InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models

TL;DR

InternSpatial introduces the largest dataset and benchmark for spatial reasoning in vision-language models, enabling improved understanding of spatial queries across diverse visual environments and instruction formats.

Contribution

It provides a large-scale, diverse dataset and a novel benchmark with multi-view reasoning tasks, advancing spatial understanding in vision-language models.

Findings

Models trained on InternSpatial improved by 12.1% on InternSpatial-Bench.

Achieved 10.7% improvement on VSI-Bench.

Maintained strong performance on general benchmarks.

Abstract

Recent benchmarks and datasets have been proposed to improve spatial reasoning in vision-language models (VLMs), yet existing open resources remain limited in scale, visual diversity, and instruction expressiveness. In this work, we introduce InternSpatial, the largest open-source dataset for spatial reasoning in VLMs, along with InternSpatial-Bench, a corresponding evaluation benchmark designed to assess spatial understanding under diverse instruction formats. InternSpatial comprises 12 million QA pairs spanning both single-view and multi-view settings, drawn from diverse visual environments and supporting 19 instruction formats that reflect varied query styles. For evaluation, we propose InternSpatial-Bench for single-view tasks and expand multi-view reasoning by introducing a novel rotation angle prediction task that has not been explored in prior work. Experimental results show that models trained on InternSpatial achieve 12.1% improvement on InternSpatial-Bench and 10.7% on VSI-Bench, while maintaining strong performance on general-purpose benchmarks. We hope these resources will support the development of spatially capable VLMs in practical applications such as robotics and embodied AI.