3DAxisPrompt: Promoting the 3D Grounding and Reasoning in GPT-4o

ICLR 2025 Conference Submission540 Authors

Keywords: visual prompt, 3D grounding, spatial casual reasoning, spatial grounding, .multimodal LLM

Abstract:

Multimodal Large Language Models (MLLMs) exhibit impressive capabilities across a variety of tasks, especially when equipped with carefully designed visual prompts. However, existing studies primarily focus on logical reasoning and visual understanding, while the capability of MLLMs to operate effectively in 3D vision remains an ongoing area of exploration.
In this paper, we introduce a novel visual prompting method called 3DAxisPrompt to elicit the 3D understanding capabilities of MLLMs in real-world scenes. More specifically, our method leverages the 3D coordinate axis and masks generated from the Segment Anything Model (SAM) to provide explicit geometric priors to MLLMs and then extend their impressive 2D grounding/reasoning ability to real-world 3D scenarios. Besides we also provide a thorough investigation of the potential visual prompting formats and conclude our findings to reveal the potential and limits of 3D understanding capabilities in GPT-4o. Finally, we build evaluation environments with four datasets, {\it i.e.} ShapeNet, ScanNet, FMB, and nuScene datasets, covering various 3D tasks. Based on this, we conduct extensive quantitative and qualitative experiments, which demonstrate the effectiveness of the proposed method. Overall, our study reveals that GPT-4o, with the help of 3DAxisPrompt, can effectively perceive an object’s 3D position in real-world scenarios. Nevertheless, a single prompt engineering approach does not consistently achieve the best outcomes for all 3D tasks. This study highlights the feasibility of leveraging MLLMs for 3D vision grounding/reasoning with prompt engineering techniques.

Primary Area: causal reasoning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 540