{"ID":2863331,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24325","arxiv_id":"2509.24325","title":"ReCon-GS: Continuum-Preserved Gaussian Streaming for Fast and Compact Reconstruction of Dynamic Scenes","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.","short_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 fidel...","url_abs":"https://arxiv.org/abs/2509.24325","url_pdf":"https://arxiv.org/pdf/2509.24325v2","authors":"[\"Jiaye Fu\",\"Qiankun Gao\",\"Chengxiang Wen\",\"Yanmin Wu\",\"Siwei Ma\",\"Jiaqi Zhang\",\"Jian Zhang\"]","published":"2025-09-29T06:23:47Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\",\"cs.MM\"]","methods":"[]","has_code":false}