Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation

• URL: http://arxiv.org/abs/2507.04047v2
• Date: Wed, 30 Jul 2025 11:32:33 GMT
• Title: Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation
• Authors: Ziyu Zhu, Xilin Wang, Yixuan Li, Zhuofan Zhang, Xiaojian Ma, Yixin Chen, Baoxiong Jia, Wei Liang, Qian Yu, Zhidong Deng, Siyuan Huang, Qing Li,
• Abstract summary: Embodied scene understanding requires not only comprehending visual-spatial information but also determining where to explore next in the 3D physical world.<n>underlinetextbf3D vision-language learning enables embodied agents to effectively explore and understand their environment.<n>model's versatility enables navigation using diverse input modalities, including categories, language descriptions, and reference images.
• Score: 54.04601077224252
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world. Existing 3D Vision-Language (3D-VL) models primarily focus on grounding objects in static observations from 3D reconstruction, such as meshes and point clouds, but lack the ability to actively perceive and explore their environment. To address this limitation, we introduce \underline{\textbf{M}}ove \underline{\textbf{t}}o \underline{\textbf{U}}nderstand (\textbf{\model}), a unified framework that integrates active perception with \underline{\textbf{3D}} vision-language learning, enabling embodied agents to effectively explore and understand their environment. This is achieved by three key innovations: 1) Online query-based representation learning, enabling direct spatial memory construction from RGB-D frames, eliminating the need for explicit 3D reconstruction. 2) A unified objective for grounding and exploring, which represents unexplored locations as frontier queries and jointly optimizes object grounding and frontier selection. 3) End-to-end trajectory learning that combines \textbf{V}ision-\textbf{L}anguage-\textbf{E}xploration pre-training over a million diverse trajectories collected from both simulated and real-world RGB-D sequences. Extensive evaluations across various embodied navigation and question-answering benchmarks show that MTU3D outperforms state-of-the-art reinforcement learning and modular navigation approaches by 14\%, 23\%, 9\%, and 2\% in success rate on HM3D-OVON, GOAT-Bench, SG3D, and A-EQA, respectively. \model's versatility enables navigation using diverse input modalities, including categories, language descriptions, and reference images. These findings highlight the importance of bridging visual grounding and exploration for embodied intelligence.

Related papers

• SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes [105.8644620467576]
  We introduce Stextscurprise3D, a novel dataset designed to evaluate language-guided spatial reasoning segmentation in complex 3D scenes.<n>Stextscurprise3D consists of more than 200k vision language pairs across 900+ detailed indoor scenes from ScanNet++ v2.<n>The dataset contains 89k+ human-annotated spatial queries deliberately crafted without object name.
  arXiv  Detail & Related papers  (2025-07-10T14:01:24Z)
• Zero-Shot 3D Visual Grounding from Vision-Language Models [10.81711535075112]
  3D Visual Grounding (3DVG) seeks to locate target objects in 3D scenes using natural language descriptions.<n>We present SeeGround, a zero-shot 3DVG framework that leverages 2D Vision-Language Models (VLMs) to bypass the need for 3D-specific training.
  arXiv  Detail & Related papers  (2025-05-28T14:53:53Z)
• AS3D: 2D-Assisted Cross-Modal Understanding with Semantic-Spatial Scene Graphs for 3D Visual Grounding [15.944945244005952]
  3D visual grounding aims to localize the unique target described by natural languages in 3D scenes.<n>We propose a novel 2D-assisted 3D visual grounding framework that constructs semantic-spatial scene graphs with referred object discrimination for relationship perception.
  arXiv  Detail & Related papers  (2025-05-07T02:02:15Z)
• AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring [49.78120051062641]
  3D visual grounding aims to correlate a natural language description with the target object within a 3D scene.<n>Existing approaches commonly encounter a shortage of text3D pairs available for training.<n>We propose AugRefer, a novel approach for advancing 3D visual grounding.
  arXiv  Detail & Related papers  (2025-01-16T09:57:40Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• SUGAR: Pre-training 3D Visual Representations for Robotics [85.55534363501131]
  We introduce a novel 3D pre-training framework for robotics named SUGAR. SUGAR captures semantic, geometric and affordance properties of objects through 3D point clouds. We show that SUGAR's 3D representation outperforms state-of-the-art 2D and 3D representations.
  arXiv  Detail & Related papers  (2024-04-01T21:23:03Z)
• Volumetric Environment Representation for Vision-Language Navigation [66.04379819772764]
  Vision-language navigation (VLN) requires an agent to navigate through a 3D environment based on visual observations and natural language instructions. We introduce a Volumetric Environment Representation (VER), which voxelizes the physical world into structured 3D cells. VER predicts 3D occupancy, 3D room layout, and 3D bounding boxes jointly.
  arXiv  Detail & Related papers  (2024-03-21T06:14:46Z)
• Weakly-Supervised 3D Visual Grounding based on Visual Linguistic Alignment [26.858034573776198]
  We propose a weakly supervised approach for 3D visual grounding based on Visual Linguistic Alignment.<n>Our 3D-VLA exploits the superior ability of current large-scale vision-language models on aligning the semantics between texts and 2D images.<n>During the inference stage, the learned text-3D correspondence will help us ground the text queries to the 3D target objects even without 2D images.
  arXiv  Detail & Related papers  (2023-12-15T09:08:14Z)
• Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding [56.00186960144545]
  3D visual grounding is the task of localizing the object in a 3D scene which is referred by a description in natural language. We propose a dense 3D grounding network, featuring four novel stand-alone modules that aim to improve grounding performance.
  arXiv  Detail & Related papers  (2023-09-08T19:27:01Z)
• Self-supervised 3D Semantic Representation Learning for Vision-and-Language Navigation [30.429893959096752]
  We develop a novel training framework to encode the voxel-level 3D semantic reconstruction into a 3D semantic representation. We construct an LSTM-based navigation model and train it with the proposed 3D semantic representations and BERT language features on vision-language pairs. Experiments show that the proposed approach achieves success rates of 68% and 66% on the validation unseen and test unseen splits of the R2R dataset.
  arXiv  Detail & Related papers  (2022-01-26T07:43:47Z)

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.