MM-Spatial：探索多模态大语言模型中的三维空间理解能力

MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs

March 17, 2025

作者: Erik Daxberger, Nina Wenzel, David Griffiths, Haiming Gang, Justin Lazarow, Gefen Kohavi, Kai Kang, Marcin Eichner, Yinfei Yang, Afshin Dehghan, Peter Grasch

cs.AI

摘要

多模态大语言模型（MLLMs）在二维视觉理解方面表现出色，但在三维空间推理能力上仍显不足。本研究利用大规模高质量的三维场景数据及开放集标注，引入了：1）一个新颖的监督微调数据集；2）一个专注于室内场景的新评估基准。我们的“万物立方化视觉问答”（CA-VQA）数据涵盖了多样化的空间任务，包括空间关系预测、度量尺寸与距离估计以及三维定位。我们展示了CA-VQA如何助力训练出MM-Spatial，这一强大的通用型MLLM，不仅在包括我们自建基准在内的三维空间理解测试中达到了顶尖水平，还证明了结合度量深度和多视角输入（CA-VQA中提供）能进一步提升三维理解能力。此外，仅凭数据，我们的模型便实现了与专用单目深度估计模型相媲美的深度感知能力。我们将公开我们的监督微调数据集及评估基准。

English

Multimodal large language models (MLLMs) excel at 2D visual understanding but remain limited in their ability to reason about 3D space. In this work, we leverage large-scale high-quality 3D scene data with open-set annotations to introduce 1) a novel supervised fine-tuning dataset and 2) a new evaluation benchmark, focused on indoor scenes. Our Cubify Anything VQA (CA-VQA) data covers diverse spatial tasks including spatial relationship prediction, metric size and distance estimation, and 3D grounding. We show that CA-VQA enables us to train MM-Spatial, a strong generalist MLLM that also achieves state-of-the-art performance on 3D spatial understanding benchmarks, including our own. We show how incorporating metric depth and multi-view inputs (provided in CA-VQA) can further improve 3D understanding, and demonstrate that data alone allows our model to achieve depth perception capabilities comparable to dedicated monocular depth estimation models. We will publish our SFT dataset and benchmark.