DSD-GS: Dynamic-Static Decomposition of Gaussian Splatting for Efficient and High-Fidelity Dynamic Scene Reconstruction

• URL: http://arxiv.org/abs/2605.30863v1
• Date: Fri, 29 May 2026 05:38:00 GMT
• Title: DSD-GS: Dynamic-Static Decomposition of Gaussian Splatting for Efficient and High-Fidelity Dynamic Scene Reconstruction
• Abstract summary: We propose a novel dynamic reconstruction framework built upon an efficient static-dynamic decomposition strategy.<n>By eliminating redundant computations on static regions, our method achieves state-of-the-art performance.<n>On the Neural 3D dataset, our framework requires only 10 minutes for training and achieves a rendering speed of over 700 FPS.
• Score: 1.0323063834827415
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dynamic scene reconstruction and novel view synthesis are fundamental to next-generation visual intelligence applications such as virtual reality, robotics, and digital twins. However, high-fidelity reconstruction of complex, time-varying scenes from arbitrary viewpoints remains a significant challenge. Existing dynamic 3DGS methods suffer from computational inefficiency, since they model all Gaussians as dynamic components. While recent decomposition-based approaches address this issue, they still struggle with degraded reconstruction quality and prolonged training time. To mitigate these limitations, we propose a novel dynamic reconstruction framework built upon an efficient static-dynamic decomposition strategy using a Feed-Forward Gaussian Splatting encoder and an optical flow model. By eliminating redundant computations on static regions, our method achieves state-of-the-art performance, outperforming existing baselines across rendering quality, training and rendering speed, and storage efficiency. Notably, on the Neural 3D dataset, our framework requires only 10 minutes for training and achieves a rendering speed of over 700 FPS on a single NVIDIA RTX 5090 GPU at resolution of 1352x1014. Furthermore, our decomposition strategy eliminates the need for COLMAP preprocessing and enables deterministic initialization, thereby enhancing both efficiency and reproducibility.

Related papers

• ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video [51.2815592637053]
  ReconPhys is a feedforward framework that jointly learns physical attribute estimation and 3D Gaussian Splatting reconstruction from a single monocular video.<n>Our method employs a dual-branch architecture trained via a self-supervised strategy, eliminating the need for ground-truth physics labels.<n> Experiments on a large-scale synthetic dataset demonstrate superior performance.
  arXiv  Detail & Related papers  (2026-04-09T06:51:14Z)
• R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splatting [59.29134814041703]
  Physical adversarial camouflage poses a severe security threat to autonomous driving systems.<n>Current methods fail to generalize across diverse geometric (e.g., viewing configurations) and radiometric variations.<n>We propose the Relightable Physical 3D Gaussian Splatting framework (R-PGA)
  arXiv  Detail & Related papers  (2026-03-27T04:38:04Z)
• HGS: Hybrid Gaussian Splatting with Static-Dynamic Decomposition for Compact Dynamic View Synthesis [28.010228209648293]
  We propose a compact and efficient framework to disentangle static and dynamic regions of a scene within a unified representation.<n> Experimental results demonstrate that our method reduces model size by up to 98% and achieves real-time rendering at up to 125 FPS at 4K resolution.
  arXiv  Detail & Related papers  (2025-12-16T12:29:00Z)
• MAPo : Motion-Aware Partitioning of Deformable 3D Gaussian Splatting for High-Fidelity Dynamic Scene Reconstruction [13.28997490352807]
  We introduce Motion-Aware Partitioning of Deformable 3D Gaussian Splatting (MAPo)<n>MAPo is a novel framework for high-fidelity dynamic scene reconstruction.<n>It achieves superior rendering quality compared to baselines while maintaining comparable computational costs.
  arXiv  Detail & Related papers  (2025-08-27T11:10:46Z)
• SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction [5.818188539758898]
  We present SD-GS, a compact and efficient dynamic splatting framework for complex dynamic scene reconstruction.<n>We also present a deformation-aware densification strategy that adaptively grows anchors in under-reconstructed high-dynamic regions.<n> Experimental results demonstrate that SD-GS achieves an average of 60% reduction in model size and an average of 100% improvement in FPS.
  arXiv  Detail & Related papers  (2025-07-10T06:35:03Z)
• DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos [52.46386528202226]
  We introduce the Deformable Gaussian Splats Large Reconstruction Model (DGS-LRM)<n>It is the first feed-forward method predicting deformable 3D Gaussian splats from a monocular posed video of any dynamic scene.<n>It achieves performance on par with state-of-the-art monocular video 3D tracking methods.
  arXiv  Detail & Related papers  (2025-06-11T17:59:58Z)
• QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization [69.50126552763157]
  Surface reconstruction is fundamental to computer vision and graphics, enabling applications in 3D modeling, mixed reality, robotics, and more.<n>Existing approaches based on rendering obtain promising results, but optimize on a per-scene basis, resulting in a slow optimization that can struggle to model textureless regions.<n>We introduce QuickSplat, which learns data-driven priors to generate dense initializations for 2D gaussian splatting optimization of large-scale indoor scenes.
  arXiv  Detail & Related papers  (2025-05-08T18:43:26Z)
• 3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene Reconstruction [1.2603104712715607]
  This paper proposes a novel 3D Gaussian point distribution method for dynamic street scene reconstruction.<n>Our approach eliminates moving objects while preserving high-fidelity static scene details.<n> Experimental results demonstrate that our method achieves high reconstruction quality, improved rendering performance, and adaptability in large-scale dynamic environments.
  arXiv  Detail & Related papers  (2025-03-15T05:41:59Z)
• 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)
• Event3DGS: Event-Based 3D Gaussian Splatting for High-Speed Robot Egomotion [54.197343533492486]
  Event3DGS can reconstruct high-fidelity 3D structure and appearance under high-speed egomotion. Experiments on multiple synthetic and real-world datasets demonstrate the superiority of Event3DGS compared with existing event-based dense 3D scene reconstruction frameworks. Our framework also allows one to incorporate a few motion-blurred frame-based measurements into the reconstruction process to further improve appearance fidelity without loss of structural accuracy.
  arXiv  Detail & Related papers  (2024-06-05T06:06:03Z)
• VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesis [73.50359502037232]
  VoxNeRF is a novel approach to enhance the quality and efficiency of neural indoor reconstruction and novel view synthesis.<n>We propose an efficient voxel-guided sampling technique that allocates computational resources to selectively the most relevant segments of rays.<n>Our approach is validated with extensive experiments on ScanNet and ScanNet++.
  arXiv  Detail & Related papers  (2023-11-09T11:32:49Z)

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.