Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding
This addresses the problem of limited 3D comprehension in AI models for applications in robotics and augmented reality, representing a novel method for a known bottleneck.
The paper tackles the challenge of spatial understanding in 3D environments for multimodal large language models by proposing Video-3D LLM, which treats 3D scenes as dynamic videos with 3D position encoding, achieving state-of-the-art performance on benchmarks like ScanRefer and SQA3D.
The rapid advancement of Multimodal Large Language Models (MLLMs) has significantly impacted various multimodal tasks. However, these models face challenges in tasks that require spatial understanding within 3D environments. Efforts to enhance MLLMs, such as incorporating point cloud features, have been made, yet a considerable gap remains between the models' learned representations and the inherent complexity of 3D scenes. This discrepancy largely stems from the training of MLLMs on predominantly 2D data, which restricts their effectiveness in comprehending 3D spaces. To address this issue, in this paper, we propose a novel generalist model, i.e., Video-3D LLM, for 3D scene understanding. By treating 3D scenes as dynamic videos and incorporating 3D position encoding into these representations, our Video-3D LLM aligns video representations with real-world spatial contexts more accurately. In addition, we have implemented a maximum coverage sampling technique to optimize the trade-off between computational cost and performance. Extensive experiments demonstrate that our model achieves state-of-the-art performance on several 3D scene understanding benchmarks, including ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, and SQA3D.