SpatialForge: Bootstrapping 3D-Aware Spatial Reasoning from Open-World 2D Images

TL;DR

SpatialForge introduces a scalable pipeline to generate large-scale 3D spatial reasoning data from 2D images, significantly enhancing vision-language models' understanding of spatial relationships.

Contribution

We propose a novel data synthesis pipeline that converts in-the-wild 2D images into structured spatial reasoning supervision, creating the 10 million QA pairs dataset SpatialForge-10M.

Findings

Training on SpatialForge-10M improves spatial reasoning in VLMs.

The dataset covers depth, layout, and viewpoint-dependent reasoning.

Experiments show significant performance gains on spatial benchmarks.

Abstract

Recent advancements in Large Vision-Language Models (VLMs) have demonstrated exceptional semantic understanding, yet these models consistently struggle with spatial reasoning, often failing at fundamental geometric tasks such as depth ordering and precise coordinate grounding. Recent efforts introduce spatial supervision from scene-centric datasets (e.g., multi-view scans or indoor video), but are constrained by the limited number of underlying scenes. As a result, the scale and diversity of such data remain significantly smaller than those of web-scale 2D image collections. To address this limitation, we propose SpatialForge, a scalable data synthesis pipeline that transforms in-the-wild 2D images into spatial reasoning supervision. Our approach decomposes spatial reasoning into perception and relation, and constructs structured supervision signals covering depth, layout, and viewpoint-dependent reasoning, with automatic verification to ensure data quality. Based on this pipeline, we build SpatialForge-10M, a large-scale dataset containing 10 million spatial QA pairs. Extensive experiments across multiple spatial reasoning benchmarks demonstrate that training on SpatialForge-10M significantly improves the spatial reasoning ability of standard VLMs, highlighting the effectiveness of scaling 2D data for 3D-aware spatial reasoning.