Saved in:
Bibliographic Details
Main Authors: Luo, Zhanpeng, Zhang, Ce, Yong, Silong, Dai, Cunxi, Wang, Qianwei, Ran, Haoxi, Shi, Guanya, Sycara, Katia, Xie, Yaqi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.00905
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910036797685760
author Luo, Zhanpeng
Zhang, Ce
Yong, Silong
Dai, Cunxi
Wang, Qianwei
Ran, Haoxi
Shi, Guanya
Sycara, Katia
Xie, Yaqi
author_facet Luo, Zhanpeng
Zhang, Ce
Yong, Silong
Dai, Cunxi
Wang, Qianwei
Ran, Haoxi
Shi, Guanya
Sycara, Katia
Xie, Yaqi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00905
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning
Luo, Zhanpeng
Zhang, Ce
Yong, Silong
Dai, Cunxi
Wang, Qianwei
Ran, Haoxi
Shi, Guanya
Sycara, Katia
Xie, Yaqi
Computer Vision and Pattern Recognition
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.
title pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.00905