Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning

arXiv:2602.21186v2 Announce Type: replace Abstract: Vision-language models excel at 2D visual understanding but remain limited in 3D spatial reasoning. Existing approaches either depend on explicit 3D modalities, which limits scalability, or inject partial, view-conditioned geometric priors and leave the language model to recover global scene structure from sparse cues. We introduce Spa3R, a self-supervised framework that learns a unified, view-invariant spatial representation from unposed multi-view RGB images. Its Predictive Spatial Field Modeling objective compresses context views into a compact latent representation and predicts aligned geometric and semantic feature fields at novel viewpoints, thereby encouraging coherent encoding of scene geometry and layout. We integrate the pre-trained Spa3R Encoder into a vision-language model through a lightweight residual cross-attention adapter, yielding Spa3-VLM and grounding language reasoning in global spatial context. Spa3-VLM achieves an average score of 58.6% on VSI-Bench and delivers leading or competitive performance across three additional spatial reasoning benchmarks. These results demonstrate that predictive spatial representation learning provides an effective visual foundation for 3D reasoning.

Related

• World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning
• StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation
• HiSC: Hierarchical Spatial Clustering Token Compression for Efficient 3D Scene Understanding

Source: arXiv cs.CV | 2026-08-14