OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping

2026-07-01

AI Summary

Existing multimodal large language models struggle to dynamically switch between camera-, object-, or direction-centered reference frames during complex spatial reasoning, often leading to failures in multi-step inference. This work proposes Multiview Perspective Spatial Mapping (MPSM), which constructs query-aligned visual cognitive graphs and textual spatial graphs, and introduces a tool-guided egocentric reasoning strategy together with a cognitive graph distillation mechanism. For the first time, this approach enables consistent and efficient spatial reasoning without relying on external geometric pipelines. It achieves state-of-the-art performance on both single-image and multi-image benchmarks, and the distilled model substantially reduces dependence on external geometric processing while preserving strong reasoning capabilities.

Abstract

Spatial intelligence remains a persistent challenge for Multimodal Large Language Models (MLLMs), as it requires coherent spatial scene representations beyond basic object recognition. Existing methods typically build such representations through textual reasoning or 3D reconstruction. However, they often falter during multi-step reasoning, particularly when required to dynamically re-anchor evidence to the specific camera-, object-, or direction-centric reference frames demanded by complex queries. To address this, we propose OmniView-Space, a framework designed to maintain spatial consistency through multimodal egocentric evidence. Our approach consists of three core components: (1) Multi-Perspective Spatial Mapping (MPSM), which re-anchors reconstructed geometry into a query-aligned visual cognitive map and a textual spatial graph; (2) Tool-Guided Egocentric Reasoning, an interleaved policy trained to actively select the ego anchor required by the query and request the corresponding MPSM evidence; and (3) Cognitive-Map Distillation, which uses MPSM-generated trajectories and ego-frame rewards to train the model to reason with self-generated cognitive maps. Experiments on single- and multi-image spatial reasoning benchmarks show that OmniView-Space achieves state-of-the-art performance. Furthermore, the distilled model maintains this performance while reducing reliance on external geometry pipelines.

Problem

• spatial reasoning
• multimodal large language models
• reference frames
• spatial representation
• egocentric reasoning

Innovation

• Multi-Perspective Spatial Mapping
• Egocentric Reasoning
• Cognitive-Map Distillation
• Spatial Reasoning
• Multimodal Large Language Models