# MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues

DevFeed: [MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues](<https://devfeed.tech/articles/mot3dvg-a-benchmark-for-outdoor-3d-visual-grounding-with-motion-aware-descriptions-and-temporal-cues-126103.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11334>)

Author: Shijia Zhao, Xusheng Guo, Qiming Xia, Xun Huang, Kezheng Xiong, Zhihong Liu, Chenglu Wen

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [autonomous vehicles](<https://devfeed.tech/topics/autonomous-vehicles.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [autonomous-driving](<https://devfeed.tech/tags/autonomous-driving.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [encoding](<https://devfeed.tech/tags/encoding.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [framework](<https://devfeed.tech/tags/framework.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [language](<https://devfeed.tech/tags/language.md>), [motion](<https://devfeed.tech/tags/motion.md>), [outdoor](<https://devfeed.tech/tags/outdoor.md>), [temporal](<https://devfeed.tech/tags/temporal.md>)

## AI overview

MoT3DVG targets outdoor 3D visual grounding, where static descriptions used in much existing work do not capture moving objects over time. Built from nuScenes, it contains 850 scenarios, 31,128 frames, and 144,568 motion-aware language prompts for dynamic objects. The authors also propose DynaVG, which adds a Short-Long Integrated Dynamic Encoding (SLIDE) module before language-point cloud alignment. SLIDE combines local motion cues through short-term window encoding with broader temporal context through long-term window shifting. The abstract reports state-of-the-art performance on MoT3DVG, but gives no metrics or further experimental details.

## Source excerpt

arXiv:2611.11334v1 Announce Type: cross Abstract: 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.