pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning

2026-02-28

AI Summary

This work addresses the limitations of multimodal large language models in 3D spatial understanding by introducing the first zero-shot, fine-tuning-free framework for 3D spatial reasoning. The proposed method guides a multimodal large language model to generate executable Python vision programs that invoke specialized tools—including 3D reconstruction, camera pose estimation, and novel view synthesis—to transform a sequence of 2D images into an interactive 3D scene, thereby enabling explicit spatial reasoning. Evaluated on MindCube and Omni3D-Bench, the approach significantly outperforms existing baselines, achieving a 12.94% improvement over GPT-4.1-mini, and successfully generates feasible navigation paths in real-world indoor environments.

Technology Category

Computer Vision: 3D Computer VisionMachine Learning: Large Multimodal Models (LMMs)Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

Search and Retrieval-Augmented AI: Large language models for searchGraph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphsSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Multi-modal Large Language Models (MLLMs) have demonstrated strong capabilities in general-purpose perception and reasoning, but they still struggle with tasks that require spatial understanding of the 3D world. To address this, we introduce pySpatial, a visual programming framework that equips MLLMs with the ability to interface with spatial tools via Python code generation. Given an image sequence and a natural-language query, the model composes function calls to spatial tools including 3D reconstruction, camera-pose recovery, novel-view rendering, etc. These operations convert raw 2D inputs into an explorable 3D scene, enabling MLLMs to reason explicitly over structured spatial representations. Notably, pySpatial requires no gradient-based fine-tuning and operates in a fully zero-shot setting. Experimental evaluations on the challenging MindCube and Omni3D-Bench benchmarks demonstrate that our framework pySpatial consistently surpasses strong MLLM baselines; for instance, it outperforms GPT-4.1-mini by 12.94% on MindCube. Furthermore, we conduct real-world indoor navigation experiments where the robot can successfully traverse complex environments using route plans generated by pySpatial, highlighting the practical effectiveness of our approach.

Problem

• spatial reasoning
• 3D understanding
• multi-modal large language models
• zero-shot learning

Innovation

• visual programming
• zero-shot spatial reasoning
• 3D reconstruction
• multi-modal LLMs
• Python code generation