Related papers: LVD-GS: Gaussian Splatting SLAM for Dynamic Scenes via Hierarchical Explicit-Implicit Representation Collaboration Rendering

LVD-GS: Gaussian Splatting SLAM for Dynamic Scenes via Hierarchical Explicit-Implicit Representation Collaboration Rendering

URL: http://arxiv.org/abs/2510.22669v1
Date: Sun, 26 Oct 2025 13:16:39 GMT
Title: LVD-GS: Gaussian Splatting SLAM for Dynamic Scenes via Hierarchical Explicit-Implicit Representation Collaboration Rendering
Authors: Wenkai Zhu, Xu Li, Qimin Xu, Benwu Wang, Kun Wei, Yiming Peng, Zihang Wang,
Abstract summary: 3D Gaussian Splatting SLAM has emerged as a widely used technique for high-fidelity mapping in spatial intelligence.<n>Existing methods often rely on a single representation scheme, which limits their performance in large-scale dynamic outdoor scenes.<n>We propose textbfLVD-GS, a novel LiDAR-Visual 3D Gaussian Splatting SLAM system.
Score: 21.615484471658842
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: 3D Gaussian Splatting SLAM has emerged as a widely used technique for high-fidelity mapping in spatial intelligence. However, existing methods often rely on a single representation scheme, which limits their performance in large-scale dynamic outdoor scenes and leads to cumulative pose errors and scale ambiguity. To address these challenges, we propose \textbf{LVD-GS}, a novel LiDAR-Visual 3D Gaussian Splatting SLAM system. Motivated by the human chain-of-thought process for information seeking, we introduce a hierarchical collaborative representation module that facilitates mutual reinforcement for mapping optimization, effectively mitigating scale drift and enhancing reconstruction robustness. Furthermore, to effectively eliminate the influence of dynamic objects, we propose a joint dynamic modeling module that generates fine-grained dynamic masks by fusing open-world segmentation with implicit residual constraints, guided by uncertainty estimates from DINO-Depth features. Extensive evaluations on KITTI, nuScenes, and self-collected datasets demonstrate that our approach achieves state-of-the-art performance compared to existing methods.

Related papers

GS-DMSR: Dynamic Sensitive Multi-scale Manifold Enhancement for Accelerated High-Quality 3D Gaussian Splatting [10.403503628255885]
Experimental results demonstrate that this method achieves a frame rate of up to 96 FPS on synthetic datasets.<n>This research integrates a multi-scale manifold enhancement module to enhance the modeling efficiency for complex deformation scenes.
arXiv Detail & Related papers (2026-01-09T07:12:23Z)
Interlaced dynamic XCT reconstruction with spatio-temporal implicit neural representations [0.0]
We investigate the use of of-Implicit Neural Representations for dynamic X-ray computed tomography (XCT) reconstruction under interlaced acquisition schemes.<n>The proposed approach combines ADMM-based optimization with INCODE, a conditioning framework incorporating prior knowledge, to enable efficient convergence.<n>Across all settings, our model achieves strong performance robustness and outperforms Time-Inter Model-Based Iter Reconstruction (TIMBIR), a state-of-the-art model-based iterative method.
arXiv Detail & Related papers (2025-10-09T01:33:58Z)
Towards Efficient General Feature Prediction in Masked Skeleton Modeling [59.46799426434277]
We propose a novel General Feature Prediction framework (GFP) for efficient mask skeleton modeling.<n>Our key innovation is replacing conventional low-level reconstruction with high-level feature prediction that spans from local motion patterns to global semantic representations.
arXiv Detail & Related papers (2025-09-03T18:05:02Z)
Laplacian Analysis Meets Dynamics Modelling: Gaussian Splatting for 4D Reconstruction [9.911802466255653]
We propose a novel dynamic 3DGS framework with hybrid explicit-implicit functions.<n>Our method demonstrates state-of-the-art performance in reconstructing complex dynamic scenes, achieving better reconstruction fidelity.
arXiv Detail & Related papers (2025-08-07T01:39:29Z)
HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene [11.906835503107189]
We propose HAIF-GS, a unified framework that enables structured and consistent dynamic modeling through sparse anchor-driven deformation.<n>We show that HAIF-GS significantly outperforms prior dynamic 3DGS methods in rendering quality, temporal coherence, and reconstruction efficiency.
arXiv Detail & Related papers (2025-06-11T08:45:08Z)
Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting [95.61137026932062]
Intern-GS is a novel approach to enhance the process of sparse-view Gaussian splatting.<n>We show that Intern-GS achieves state-of-the-art rendering quality across diverse datasets.
arXiv Detail & Related papers (2025-05-27T05:17:49Z)
Event-boosted Deformable 3D Gaussians for Dynamic Scene Reconstruction [50.873820265165975]
We introduce the first approach combining event cameras, which capture high-temporal-resolution, continuous motion data, with deformable 3D-GS for dynamic scene reconstruction.<n>We propose a GS-Threshold Joint Modeling strategy, creating a mutually reinforcing process that greatly improves both 3D reconstruction and threshold modeling.<n>We contribute the first event-inclusive 4D benchmark with synthetic and real-world dynamic scenes, on which our method achieves state-of-the-art performance.
arXiv Detail & Related papers (2024-11-25T08:23:38Z)
Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation [60.80423207808076]
Capturing long-range dependencies while preserving high-resolution visual representations is crucial for dense prediction tasks such as human pose estimation.<n>We propose the Dynamic Visual State Space (DVSS) block, which augments visual state space models with multi-scale convolutional operations.<n>We build HRVMamba, a novel model for efficient high-resolution representation learning.
arXiv Detail & Related papers (2024-10-04T06:19:29Z)
DENSER: 3D Gaussians Splatting for Scene Reconstruction of Dynamic Urban Environments [0.0]
We propose DENSER, a framework that significantly enhances the representation of dynamic objects. The proposed approach significantly outperforms state-of-the-art methods by a wide margin.
arXiv Detail & Related papers (2024-09-16T07:11:58Z)
Learn to Memorize and to Forget: A Continual Learning Perspective of Dynamic SLAM [17.661231232206028]
Simultaneous localization and mapping (SLAM) with implicit neural representations has received extensive attention. We propose a novel SLAM framework for dynamic environments.
arXiv Detail & Related papers (2024-07-18T09:35:48Z)
SMORE: Simultaneous Map and Object REconstruction [66.66729715211642]
We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR.<n>We take a holistic perspective and optimize a compositional model of a dynamic scene that decomposes the world into rigidly-moving objects and the background.
arXiv Detail & Related papers (2024-06-19T23:53:31Z)
Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstruction [89.53963284958037]
We propose a novel motion-aware enhancement framework for dynamic scene reconstruction. Specifically, we first establish a correspondence between 3D Gaussian movements and pixel-level flow. For the prevalent deformation-based paradigm that presents a harder optimization problem, a transient-aware deformation auxiliary module is proposed.
arXiv Detail & Related papers (2024-03-18T03:46:26Z)
Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance. We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
arXiv Detail & Related papers (2023-05-22T12:18:20Z)

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