ReCon-GS: Continuum-Preserved Gaussian Streaming for Fast and Compact Reconstruction of Dynamic Scenes

• URL: http://arxiv.org/abs/2509.24325v2
• Date: Thu, 30 Oct 2025 13:38:59 GMT
• Title: ReCon-GS: Continuum-Preserved Gaussian Streaming for Fast and Compact Reconstruction of Dynamic Scenes
• Authors: Jiaye Fu, Qiankun Gao, Chengxiang Wen, Yanmin Wu, Siwei Ma, Jiaqi Zhang, Jian Zhang,
• Abstract summary: ReCon-GS is a storage-aware framework that enables high fidelity online dynamic scene reconstruction and real-time rendering.<n>We show that ReCon-GS improves training efficiency by approximately 15% and achieves superior FVV synthesis quality.<n>At equivalent rendering quality, ReCon-GS slashes memory requirements by over 50% compared to leading state-of-the-art methods.
• Score: 41.108974064267436
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Online free-viewpoint video (FVV) reconstruction is challenged by slow per-frame optimization, inconsistent motion estimation, and unsustainable storage demands. To address these challenges, we propose the Reconfigurable Continuum Gaussian Stream, dubbed ReCon-GS, a novel storage-aware framework that enables high fidelity online dynamic scene reconstruction and real-time rendering. Specifically, we dynamically allocate multi-level Anchor Gaussians in a density-adaptive fashion to capture inter-frame geometric deformations, thereby decomposing scene motion into compact coarse-to-fine representations. Then, we design a dynamic hierarchy reconfiguration strategy that preserves localized motion expressiveness through on-demand anchor re-hierarchization, while ensuring temporal consistency through intra-hierarchical deformation inheritance that confines transformation priors to their respective hierarchy levels. Furthermore, we introduce a storage-aware optimization mechanism that flexibly adjusts the density of Anchor Gaussians at different hierarchy levels, enabling a controllable trade-off between reconstruction fidelity and memory usage. Extensive experiments on three widely used datasets demonstrate that, compared to state-of-the-art methods, ReCon-GS improves training efficiency by approximately 15% and achieves superior FVV synthesis quality with enhanced robustness and stability. Moreover, at equivalent rendering quality, ReCon-GS slashes memory requirements by over 50% compared to leading state-of-the-art methods.

Related papers

• LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory [97.14005794889134]
  We present LoGeR, a novel architecture that scales dense 3D reconstruction to extremely long sequences without post-optimization.<n>LoGeR processes video streams in chunks, leveraging strong bidirectional priors for high-fidelity intra-chunk reasoning.<n>This memory architecture enables LoGeR to be trained on sequences of 128 frames, and generalize up to thousands of frames during inference.
  arXiv  Detail & Related papers  (2026-03-03T18:55:37Z)
• LoD-Structured 3D Gaussian Splatting for Streaming Video Reconstruction [19.37120630668256]
  Free-Viewpoint Video (FVV) reconstruction enables photorealistic and interactive 3D scene visualization.<n>Recent 3D Gaussian Splatting (3DGS) has advanced FVV due to its superior rendering speed.<n>We propose StreamLoD-GS, an LoD-based Gaussian Splatting framework designed specifically for SFVV.
  arXiv  Detail & Related papers  (2026-01-26T13:27:46Z)
• Rethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation [75.58269386927076]
  Autoregressive (AR) models are often dismissed as impractical due to prohibitive computational cost.<n>This work re-thinks this paradigm, introducing a framework built on hierarchical parallelism and progressive adaptation.<n> Experiments on diverse datasets (natural, satellite, medical) validate that our method achieves new state-of-the-art compression.
  arXiv  Detail & Related papers  (2025-11-14T06:27:58Z)
• Flow-Matching Guided Deep Unfolding for Hyperspectral Image Reconstruction [53.26903617819014]
  Flow-Matching-guided Unfolding network (FMU) is first to integrate flow matching into HSI reconstruction.<n>To further strengthen the learned dynamics, we introduce a mean velocity loss.<n>Experiments on both simulated and real datasets show that FMU significantly outperforms existing approaches in reconstruction quality.
  arXiv  Detail & Related papers  (2025-10-02T11:32:00Z)
• Progressive Flow-inspired Unfolding for Spectral Compressive Imaging [11.638690628451647]
  Coded aperture snapshot spectral imaging (CASSI) retrieves a 3D hyperspectral image (HSI) from a single 2D compressed measurement.<n>Recent deep unfolding networks (DUNs) have achieved the state of the art in CASSI reconstruction.<n>Inspired by diffusion trajectories and flow matching, we propose a novel trajectory-controllable unfolding framework.
  arXiv  Detail & Related papers  (2025-09-15T16:10:50Z)
• 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)
• RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priors [54.81109375939306]
  RGE-GS is a novel expansive reconstruction framework that synergizes diffusion-based generation with reward-guided Gaussian integration.<n>We propose a reward network that learns to identify and prioritize consistently generated patterns prior to reconstruction phases.<n>During the reconstruction process, we devise a differentiated training strategy that automatically adjust Gaussian optimization progress according to scene converge metrics.
  arXiv  Detail & Related papers  (2025-06-28T08:02:54Z)
• EvolvingGS: High-Fidelity Streamable Volumetric Video via Evolving 3D Gaussian Representation [14.402479944396665]
  We introduce EvolvingGS, a two-stage strategy that first deforms the Gaussian model to align with the target frame, and then refines it with minimal point addition/subtraction.<n> Owing to the flexibility of the incrementally evolving representation, our method outperforms existing approaches in terms of both per-frame and temporal quality metrics.<n>Our method significantly advances the state-of-the-art in dynamic scene reconstruction, particularly for extended sequences with complex human performances.
  arXiv  Detail & Related papers  (2025-03-07T06:01:07Z)
• Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization [27.509109317973817]
  3D Gaussian Splatting (3DGS) has garnered significant attention for its high-quality rendering and fast inference speed.<n>Previous methods primarily focus on geometry regularization, with common approaches including primitive-based and dual-model frameworks.<n>We propose CarGS, a unified model leveraging-adaptive regularization to achieve simultaneous, high-quality surface reconstruction.
  arXiv  Detail & Related papers  (2025-03-02T12:51:38Z)
• Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction [3.9363268745580426]
  AT-GS is a novel method for reconstructing high-quality dynamic surfaces from multi-view videos through per-frame incremental optimization. We reduce temporal jittering in dynamic surfaces by ensuring consistency in curvature maps across consecutive frames. Our method achieves superior accuracy and temporal coherence in dynamic surface reconstruction, delivering high-fidelity space-time novel view synthesis.
  arXiv  Detail & Related papers  (2024-11-10T21:30:16Z)
• ReMatching Dynamic Reconstruction Flow [55.272357926111454]
  This work introduces the ReMatching framework, designed to improve reconstruction quality by incorporating deformation priors into dynamic reconstruction models.<n>Our approach advocates for velocity-field based priors, for which we suggest a matching procedure that can seamlessly supplement existing dynamic reconstruction pipelines.<n>Our evaluations on popular benchmarks involving both synthetic and real-world dynamic scenes demonstrate that augmenting current state-of-the-art methods with our approach leads to a clear improvement in reconstruction accuracy.
  arXiv  Detail & Related papers  (2024-11-01T16:09:33Z)
• Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition [52.89441679581216]
  Low-Light Video Enhancement (LLVE) seeks to restore dynamic or static scenes plagued by severe invisibility and noise.<n>We present an innovative video decomposition strategy that incorporates view-independent and view-dependent components.<n>Our framework consistently outperforms existing methods, establishing a new SOTA performance.
  arXiv  Detail & Related papers  (2024-05-24T15:56:40Z)

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.