AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splatting

• URL: http://arxiv.org/abs/2607.01290v2
• Date: Fri, 03 Jul 2026 06:02:45 GMT
• Title: AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splatting
• Abstract summary: 3D Gaussian Splatting (3DGS) has emerged as a powerful representation for high-fidelity rendering.<n>Existing assets often suffer from quality bottlenecks such as missing details and texture noise.<n>We propose a novel 3D-native refinement paradigm named AnchorSplat.
• Score: 45.65377534924918
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis [49.87457834078904]
  InfiniSplat is a feed-forward single-image 3DGS framework that moves from a pixel-aligned representation toward a surface-aligned representation.<n>InfiniSplat achieves state-of-the-art performance compared with single-image feed-forward baselines.
  arXiv  Detail & Related papers  (2026-08-03T16:17:39Z)
• QuerySplat: Decoupling Geometry and Appearance Representations in 3DGS Prediction [25.05567017307621]
  We propose textbfQuerySplat, a feed-forward 3DGS framework driven by geometric priors and explicit appearance decoupling.<n>Experiments demonstrate that QuerySplat mitigates the blurry rendering issues of early query-based models.<n>On the challenging DL3DV benchmark, it achieves state-of-the-art novel view synthesis performance, with average PSNR gains of 2.30 dB and 1.04 dB over the best pose-free and pose-required baselines.
  arXiv  Detail & Related papers  (2026-08-02T12:12:02Z)
• MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction [22.10774833540097]
  We propose a training framework built around direct 3D consistency supervision.<n> MAC-Splat builds on the MASt3R geometric backbone and a frozen DINOv3 encoder to obtain semantically informed 2D correspondences.<n>Experiments on ScanNet++ show that MAC-Splat outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-07-12T14:50:08Z)
• GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds [25.00064989891048]
  GSCompleter is a distillation-free plugin that shifts scene completion to a stable "Generate-then-Register" workflow.<n>Our approach first synthesizes plausible 2D reference images and explicitly lifts them into metric-scale 3D primitives via a robust Stereo-Anchor mechanism.<n>This shift to a rapid registration paradigm delivers superior 3DGS completion performance across three distinct benchmarks.
  arXiv  Detail & Related papers  (2026-04-22T03:47:25Z)
• PointSplat: Efficient Geometry-Driven Pruning and Transformer Refinement for 3D Gaussian Splatting [2.5823344978857388]
  3D Gaussian Splatting has recently unlocked real-time, high-fidelity novel view synthesis by representing scenes using explicit 3D primitives.<n>Traditional methods often require millions of Gaussians to capture complex scenes, leading to significant memory and storage demands.<n>Recent approaches have addressed this issue through pruning and per-scene fine-tuning of Gaussian parameters, thereby reducing the model size while maintaining visual quality.
  arXiv  Detail & Related papers  (2026-04-10T20:56:18Z)
• SurfSplat: Conquering Feedforward 2D Gaussian Splatting with Surface Continuity Priors [23.876164780443915]
  SurfSplat is a feedforward framework based on 2D Gaussian Splatting (2DGS) primitive.<n>By incorporating a surface continuity prior, SurfSplat reconstructs coherent geometry together with faithful textures.<n>High-Resolution Rendering Consistency (HRRC) is a new evaluation metric designed to evaluate high-resolution reconstruction quality.
  arXiv  Detail & Related papers  (2026-02-02T11:58:26Z)
• SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting [85.87902260102652]
  We introduce the novel task of Sequential 3D Gaussian Affordance Reasoning.<n>We then propose SeqSplatNet, an end-to-end framework that directly maps an instruction to a sequence of 3D affordance masks.<n>Our method sets a new state-of-the-art on our challenging benchmark, effectively advancing affordance reasoning from single-step interactions to complex, sequential tasks at the scene level.
  arXiv  Detail & Related papers  (2025-07-31T17:56:55Z)
• 3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians [82.67236400004826]
  3D affordance reasoning is essential in associating human instructions with functional regions of 3D objects.<n>We present 3DAffordSplat, the first large-scale, multi-modal dataset tailored for 3DGS-based affordance reasoning.<n>We introduce AffordSplatNet, a novel model specifically designed for affordance reasoning using 3DGS representations.
  arXiv  Detail & Related papers  (2025-04-15T14:21:47Z)
• SAGS: Structure-Aware 3D Gaussian Splatting [53.6730827668389]
  We propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene. SAGS reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark novel-view synthesis datasets.
  arXiv  Detail & Related papers  (2024-04-29T23:26:30Z)
• InstantSplat: Sparse-view Gaussian Splatting in Seconds [91.77050739918037]
  We introduce InstantSplat, a novel approach for addressing sparse-view 3D scene reconstruction at lightning-fast speed.<n>InstantSplat employs a self-supervised framework that optimize 3D scene representation and camera poses.<n>It achieves an acceleration of over 30x in reconstruction and improves visual quality (SSIM) from 0.3755 to 0.7624 compared to traditional SfM with 3D-GS.
  arXiv  Detail & Related papers  (2024-03-29T17:29:58Z)

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.