I Know About "Up"! Enhancing Spatial Reasoning in Visual Language Models Through 3D Reconstruction

Meng, Zaiqiao, Zhou, Hao, Chen, Yifang

arXiv.org Artificial Intelligence 

Visual Language Models (VLMs) are essential for various tasks, particularly visual reasoning tasks, due to their robust multi-modal information integration, visual reasoning capabilities, and contextual awareness. However, existing \VLMs{}' visual spatial reasoning capabilities are often inadequate, struggling even with basic tasks such as distinguishing left from right. To address this, we propose the \ours{} model, designed to enhance the visual spatial reasoning abilities of VLMS. ZeroVLM employs Zero-1-to-3, a 3D reconstruction model for obtaining different views of the input images and incorporates a prompting mechanism to further improve visual spatial reasoning. Experimental results on four visual spatial reasoning datasets show that our \ours{} achieves up to 19.48% accuracy improvement, which indicates the effectiveness of the 3D reconstruction and prompting mechanisms of our ZeroVLM.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found