{"ID":5675719,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-04T11:59:22.214497071Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01290","arxiv_id":"2607.01290","title":"AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splatting","abstract":"3D Gaussian Splatting (3DGS) has emerged as a powerful representation for high-fidelity rendering. However, existing assets often suffer from quality bottlenecks such as missing details and texture noise. Prior attempts to enhance these assets via 2D image processing introduce multi-view inconsistencies and high computational costs. In this paper, we propose a novel 3D-native refinement paradigm named AnchorSplat. AnchorSplat is an end-to-end deep network operating directly on 3D structures, avoiding the expensive optimization overhead of traditional 3D-2D-3D pipelines. Crucially, AnchorSplat is a strictly source-free solution requiring no original multi-view images. Central to the proposed method is the Point Anchor Mechanism, which enforces geometric consistency via local offset constraints, mitigating ill-posed mapping and gradient confounding. Furthermore, AnchorSplat replaces iterative densification with a single-pass multiplication mechanism. To facilitate research, we construct 3DGS-SR, the first large-scale benchmark for this task. Experiments demonstrate state-of-the-art results on the 3DGS-SR dataset, with throughput up to $10^5$ times faster than optimization methods. Notably, AnchorSplat exhibits robust zero-shot generalization across diverse data distributions, including generative model outputs and real-world scans.","short_abstract":"3D Gaussian Splatting (3DGS) has emerged as a powerful representation for high-fidelity rendering. However, existing assets often suffer from quality bottlenecks such as missing details and texture noise. Prior attempts to enhance these assets via 2D image processing introduce multi-view inconsistencies and high comput...","url_abs":"https://arxiv.org/abs/2607.01290","url_pdf":"https://arxiv.org/pdf/2607.01290v1","authors":"[\"Dexu Zhu\",\"Jiangnan Shao\",\"Xiaofeng Wang\",\"Junxian Duan\",\"Jie Cao\",\"Zheng Zhu\",\"Huaibo Huang\"]","published":"2026-07-01T12:14:29Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}