M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts
This addresses the problem of limited 3D task generalization for researchers and developers in AI and robotics, though it is incremental as it builds on existing multimodal models by providing a new dataset.
The authors tackled the lack of large-scale 3D instruction-following datasets for multimodal language models by introducing M3DBench, a comprehensive dataset with over 320k instruction-response pairs that unifies diverse 3D tasks, and established a benchmark showing its effectiveness in supporting general 3D-centric tasks.
Recently, 3D understanding has become popular to facilitate autonomous agents to perform further decisionmaking. However, existing 3D datasets and methods are often limited to specific tasks. On the other hand, recent progress in Large Language Models (LLMs) and Multimodal Language Models (MLMs) have demonstrated exceptional general language and imagery tasking performance. Therefore, it is interesting to unlock MLM's potential to be 3D generalist for wider tasks. However, current MLMs' research has been less focused on 3D tasks due to a lack of large-scale 3D instruction-following datasets. In this work, we introduce a comprehensive 3D instructionfollowing dataset called M3DBench, which possesses the following characteristics: 1) It supports general multimodal instructions interleaved with text, images, 3D objects, and other visual prompts. 2) It unifies diverse 3D tasks at both region and scene levels, covering a variety of fundamental abilities in real-world 3D environments. 3) It is a large-scale 3D instruction-following dataset with over 320k instruction-response pairs. Furthermore, we establish a new benchmark for assessing the performance of large models in understanding multi-modal 3D prompts. Extensive experiments demonstrate the effectiveness of our dataset and baseline, supporting general 3D-centric tasks, which can inspire future research.