MoT3DVG：面向户外动态场景的3D视觉定位基准发布
MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues
做自动驾驶或3D视觉语言方向的研究者可以看看这个新基准：85万多条不是，是14万多条带运动描述的语言标注，配合SLIDE模块能利用时间信息定位运动物体，比只处理静态室内场景的老数据集更贴近真实驾驶场景。
MoT3DVG 是一个针对户外动态场景的 3D 视觉定位（3DVG）数据集，基于 nuScenes 构建，包含 850 个场景、31,128 帧数据，并提供 144,568 条带有运动描述的语言提示。此前 3DVG 研究主要集中在静态室内物体上，难以应用于自动驾驶等动态户外环境，该数据集通过时间演化的运动描述弥补了这一空白。
论文同时提出 DynaVG 框架，在语言-点云对齐之前引入 SLIDE 模块（Short-Long Integrated Dynamic Encoding），通过短期窗口编码和长期窗口偏移来同时建模局部运动线索与全局时间上下文。实验显示 DynaVG 在 MoT3DVG 上取得了当前最优成绩，验证了运动感知编码的有效性。
该工作将 3DVG 从静态室内扩展到动态户外场景，为自动驾驶中基于自然语言的目标定位研究提供了新的评测标准，同时揭示了时间线索利用方面的开放挑战。
MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues
3D visual grounding (3DVG) localizes language-referred objects in 3D scenes, with broad applicability in both indoor and outdoor environments. However, existing 3DVG research focuses on static indoor objects, limiting its use in dynamic outdoor autonomous driving. Motion descriptions, which capture the temporal dynamics of moving objects, offer a promising way to address this challenge. We therefore introduce MoT3DVG, a large-scale dataset for dynamic-aware outdoor 3DVG with temporally evolving motion descriptions. It contains 850 scenarios with 31,128 frames from nuScenes dataset, and provides 144,568 language prompts with motion-aware descriptions for dynamic objects across time. We further propose DynaVG, a novel framework that effectively leverages temporal cues for outdoor 3DVG. In addition to the standard modality-specific encoders, DynaVG introduces a Short-Long Integrated Dynamic Encoding (SLIDE) module before the language-point cloud alignment. SLIDE models both local motion cues and global temporal context via short-term window encoding and long-term window shifting. Extensive experiments demonstrate its state-of-the-art performance on MoT3DVG, validating the effectiveness of motion-aware encoding. Our work reveals open challenges and promising directions for future research in outdoor 3DVG.
本条情报归属 AITOP「论文」核心追踪栏目。涉及核心实体与技术议题包括：3DVG、MoT3DVG、nuScenes、自动驾驶，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Shijia Zhao, Xusheng Guo, Qiming Xia, Xun Huang, Kezheng Xiong, Zhihong Liu, Chenglu Wen），经 AITOP 多维评分管线结构化提炼。