MMDrive: Interactive Scene Understanding Beyond Vision with Multi-representational Fusion

• URL: http://arxiv.org/abs/2512.13177v2
• Date: Tue, 16 Dec 2025 05:50:26 GMT
• Title: MMDrive: Interactive Scene Understanding Beyond Vision with Multi-representational Fusion
• Authors: Minghui Hou, Wei-Hsing Huang, Shaofeng Liang, Daizong Liu, Tai-Hao Wen, Gang Wang, Runwei Guan, Weiping Ding,
• Abstract summary: This study proposes MMDrive, a vision-language model framework that extends traditional image understanding to a generalized 3D scene understanding framework.<n> MMDrive incorporates three complementary modalities, including occupancy maps, LiDAR point clouds, and textual scene descriptions.<n> MMDrive achieves significant performance gains over existing vision-language models for autonomous driving, with a BLEU-4 score of 54.56 and METEOR of 41.78 on DriveLM, and an accuracy score of 62.7% on NuScenes-QA.
• Score: 39.303609347179695
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language models enable the understanding and reasoning of complex traffic scenarios through multi-source information fusion, establishing it as a core technology for autonomous driving. However, existing vision-language models are constrained by the image understanding paradigm in 2D plane, which restricts their capability to perceive 3D spatial information and perform deep semantic fusion, resulting in suboptimal performance in complex autonomous driving environments. This study proposes MMDrive, an multimodal vision-language model framework that extends traditional image understanding to a generalized 3D scene understanding framework. MMDrive incorporates three complementary modalities, including occupancy maps, LiDAR point clouds, and textual scene descriptions. To this end, it introduces two novel components for adaptive cross-modal fusion and key information extraction. Specifically, the Text-oriented Multimodal Modulator dynamically weights the contributions of each modality based on the semantic cues in the question, guiding context-aware feature integration. The Cross-Modal Abstractor employs learnable abstract tokens to generate compact, cross-modal summaries that highlight key regions and essential semantics. Comprehensive evaluations on the DriveLM and NuScenes-QA benchmarks demonstrate that MMDrive achieves significant performance gains over existing vision-language models for autonomous driving, with a BLEU-4 score of 54.56 and METEOR of 41.78 on DriveLM, and an accuracy score of 62.7% on NuScenes-QA. MMDrive effectively breaks the traditional image-only understanding barrier, enabling robust multimodal reasoning in complex driving environments and providing a new foundation for interpretable autonomous driving scene understanding.

Related papers

• LMAD: Integrated End-to-End Vision-Language Model for Explainable Autonomous Driving [58.535516533697425]
  Large vision-language models (VLMs) have shown promising capabilities in scene understanding.<n>We propose a novel vision-language framework tailored for autonomous driving, called LMAD.<n>Our framework emulates modern end-to-end driving paradigms by incorporating comprehensive scene understanding and a task-specialized structure with VLMs.
  arXiv  Detail & Related papers  (2025-08-17T15:42:54Z)
• V3LMA: Visual 3D-enhanced Language Model for Autonomous Driving [2.3302708486956454]
  We introduce V3LMA, a novel approach that enhances 3D scene understanding by integrating Large Language Models (LLMs) with LVLMs.<n>V3LMA leverages textual descriptions generated from object detections and video inputs, significantly boosting performance without requiring fine-tuning.<n>Our method improves situational awareness and decision-making in complex traffic scenarios, achieving a score of 0.56 on the LingoQA benchmark.
  arXiv  Detail & Related papers  (2025-04-30T20:00:37Z)
• VLM-E2E: Enhancing End-to-End Autonomous Driving with Multimodal Driver Attention Fusion [8.738991730715039]
  We propose VLM-E2E, a novel framework that uses the Vision-Language Models to enhance training by providing attentional cues.<n>By focusing on attentional semantics, VLM-E2E better aligns with human-like driving behavior, which is critical for navigating dynamic and complex environments.<n>We evaluate VLM-E2E on the nuScenes dataset and achieve significant improvements in perception, prediction, and planning over the baseline end-to-end model.
  arXiv  Detail & Related papers  (2025-02-25T10:02:12Z)
• Hints of Prompt: Enhancing Visual Representation for Multimodal LLMs in Autonomous Driving [55.609997552148826]
  We propose the Hints of Prompt (HoP) framework, which introduces three key enhancements.<n>These hints are fused through a Hint Fusion module, enriching visual representations by capturing driving-related representations with limited domain data.<n>Extensive experiments confirm the effectiveness of the HoP framework, showing that it significantly outperforms previous state-of-the-art methods in all key metrics.
  arXiv  Detail & Related papers  (2024-11-20T06:58:33Z)
• DeepInteraction++: Multi-Modality Interaction for Autonomous Driving [80.8837864849534]
  We introduce a novel modality interaction strategy that allows individual per-modality representations to be learned and maintained throughout.<n>DeepInteraction++ is a multi-modal interaction framework characterized by a multi-modal representational interaction encoder and a multi-modal predictive interaction decoder.<n>Experiments demonstrate the superior performance of the proposed framework on both 3D object detection and end-to-end autonomous driving tasks.
  arXiv  Detail & Related papers  (2024-08-09T14:04:21Z)
• Probing Multimodal LLMs as World Models for Driving [72.18727651074563]
  We look at the application of Multimodal Large Language Models (MLLMs) in autonomous driving. Despite advances in models like GPT-4o, their performance in complex driving environments remains largely unexplored.
  arXiv  Detail & Related papers  (2024-05-09T17:52:42Z)
• Multi-Frame, Lightweight & Efficient Vision-Language Models for Question Answering in Autonomous Driving [0.0]
  We develop an efficient, lightweight, multi-frame vision language model which performs Visual Question Answering for autonomous driving. In comparison to previous approaches, EM-VLM4AD requires at least 10 times less memory and floating point operations.
  arXiv  Detail & Related papers  (2024-03-28T21:18:33Z)
• Drive Anywhere: Generalizable End-to-end Autonomous Driving with Multi-modal Foundation Models [114.69732301904419]
  We present an approach to apply end-to-end open-set (any environment/scene) autonomous driving that is capable of providing driving decisions from representations queryable by image and text. Our approach demonstrates unparalleled results in diverse tests while achieving significantly greater robustness in out-of-distribution situations.
  arXiv  Detail & Related papers  (2023-10-26T17:56:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.