DGSG-Mind: Dynamic 3D Gaussian Scene Graphs for Long-Term Scene Understanding and Grounding

• URL: http://arxiv.org/abs/2605.29879v2
• Date: Fri, 29 May 2026 04:39:13 GMT
• Title: DGSG-Mind: Dynamic 3D Gaussian Scene Graphs for Long-Term Scene Understanding and Grounding
• Abstract summary: We present DGSG-Mind, a hybrid instance-aware 3D Gaussian dynamic scene graph system with an embodied reasoning agent.<n>We show that DGSG-Mind achieves the best zero-shot 3DVG performance among methods operating on self-reconstructed maps.<n>We also deploy DGSG-Mind on real-world robots to demonstrate its target-oriented reasoning and dynamic update capabilities.
• Score: 6.961193964556352
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Integrating open-vocabulary semantic information into dynamic 3D scene representations is essential for long-term embodied scene understanding. However, existing methods often suffer from fragile instance association due to incomplete cross-view cues, while their limited ability to handle object-level topological changes restricts long-term robotic task execution. Moreover, current 3D scene understanding methods either rely on simple feature matching without explicit spatial reasoning or assume offline ground-truth 3D geometry. To address these challenges, we present DGSG-Mind, a hybrid instance-aware 3D Gaussian dynamic scene graph system with an embodied reasoning agent. Our system couples a probabilistic voxel grid with explicit 3D Gaussians to enable robust cross-modal instance fusion and incremental semantic mapping. It handles dynamic changes through Gaussian-based visual relocalization and localized masked refinement guided by geometric-semantic consistency. Built on the instance Gaussian map, DGSG-Mind further constructs a hierarchical scene graph and develops the 3D Gaussian Mind, which integrates structural relations, spatial-semantic information, and visually annotated RoI Gaussian renderings for multimodal reasoning. Extensive experiments show that DGSG-Mind achieves the best zero-shot 3DVG performance among methods operating on self-reconstructed maps, while also delivering strong performance in 3D open-vocabulary semantic segmentation and scene reconstruction. We further deploy DGSG-Mind on real-world robots to demonstrate its target-oriented reasoning and dynamic update capabilities. The project page of DGSG-Mind is available at https://icr-lab.github.io/DGSG-Mind

Related papers

• Graph-GSReg: Leveraging 3D Scene Graphs for Gaussian Splatting Registration [21.225937272344968]
  Merging multiple 3D Gaussian Splatting (3DGS) scenes into a single unified representation is essential for large-scale 3D mapping and map management.<n>Previous methods attempt direct correspondence between Gaussian primitives and require training on large 3DGS.<n>Our method constructs a 3D scene graph from a 3DGS and its rendered images, textitreformulating 3DGS registration as a graph registration problem
  arXiv  Detail & Related papers  (2026-06-29T04:58:44Z)
• Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding [50.098085774845195]
  We propose a paradigm shift by leveraging the implicit spatial prior within large-scale generation models.<n>We introduce GeneEGA-3D (Video Extracted Generative Awareness), a plug-and-play framework that repurposes a pre-trained video diffusion model as a Latent World Simulator.
  arXiv  Detail & Related papers  (2026-03-19T17:59:58Z)
• OGScene3D: Incremental Open-Vocabulary 3D Gaussian Scene Graph Mapping for Scene Understanding [30.730672505996967]
  OGScene3D is an open-vocabulary scene understanding system that achieves accurate 3D semantic mapping and scene graph construction incrementally.<n>Our system employs a confidence-based Gaussian semantic representation that jointly models semantic predictions and their reliability.<n>By integrating 2D-3D semantic consistency with Gaussian rendering contribution, this method continuously refines the semantic understanding of the entire scene.
  arXiv  Detail & Related papers  (2026-03-17T09:38:01Z)
• SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting [85.87902260102652]
  We introduce the novel task of Sequential 3D Gaussian Affordance Reasoning.<n>We then propose SeqSplatNet, an end-to-end framework that directly maps an instruction to a sequence of 3D affordance masks.<n>Our method sets a new state-of-the-art on our challenging benchmark, effectively advancing affordance reasoning from single-step interactions to complex, sequential tasks at the scene level.
  arXiv  Detail & Related papers  (2025-07-31T17:56:55Z)
• Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs [16.153129392697885]
  We introduce a training-free framework that constructs a superpoint graph directly from Gaussian primitives.<n>The superpoint graph partitions the scene into spatially compact and semantically coherent regions, forming view-consistent 3D entities.<n>Our method achieves state-of-the-art open-vocabulary segmentation performance, with semantic field reconstruction completed over $30times$ faster.
  arXiv  Detail & Related papers  (2025-04-17T17:56:07Z)
• GaussianGraph: 3D Gaussian-based Scene Graph Generation for Open-world Scene Understanding [20.578106363482018]
  We propose a novel framework that enhances 3DGS-based scene understanding by integrating semantic clustering and scene graph generation.<n>We introduce a "Control-Follow" clustering strategy, which dynamically adapts to scene scale and feature distribution, avoiding feature compression.<n>We enrich scene representation by integrating object attributes and spatial relations extracted from 2D foundation models.
  arXiv  Detail & Related papers  (2025-03-06T02:36:59Z)
• OVGaussian: Generalizable 3D Gaussian Segmentation with Open Vocabularies [112.80292725951921]
  textbfOVGaussian is a generalizable textbfOpen-textbfVocabulary 3D semantic segmentation framework based on the 3D textbfGaussian representation.<n>We first construct a large-scale 3D scene dataset based on 3DGS, dubbed textbfSegGaussian, which provides detailed semantic and instance annotations for both Gaussian points and multi-view images.<n>To promote semantic generalization across scenes, we introduce Generalizable Semantic Rasterization (GSR), which leverages a
  arXiv  Detail & Related papers  (2024-12-31T07:55:35Z)
• Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding [59.51535163599723]
  FreeGS is an unsupervised semantic-embedded 3DGS framework that achieves view-consistent 3D scene understanding without the need for 2D labels.<n>FreeGS performs comparably to state-of-the-art methods while avoiding the complex data preprocessing workload.
  arXiv  Detail & Related papers  (2024-11-29T08:52:32Z)
• HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting [53.6394928681237]
  holistic understanding of urban scenes based on RGB images is a challenging yet important problem. Our main idea involves the joint optimization of geometry, appearance, semantics, and motion using a combination of static and dynamic 3D Gaussians. Our approach offers the ability to render new viewpoints in real-time, yielding 2D and 3D semantic information with high accuracy.
  arXiv  Detail & Related papers  (2024-03-19T13:39:05Z)
• Incremental 3D Semantic Scene Graph Prediction from RGB Sequences [86.77318031029404]
  We propose a real-time framework that incrementally builds a consistent 3D semantic scene graph of a scene given an RGB image sequence. Our method consists of a novel incremental entity estimation pipeline and a scene graph prediction network. The proposed network estimates 3D semantic scene graphs with iterative message passing using multi-view and geometric features extracted from the scene entities.
  arXiv  Detail & Related papers  (2023-05-04T11:32:16Z)

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.