发表机构
Jinan University（暨南大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
VCAR是一种无需训练的3DGS分割策略，通过粗阶段的可见性加权多视图投票、细阶段的球形螺旋采样补充视角及轴感知边界优化，在NVOS和LERF数据集上实现了最优的分割精度与效率。
AI 中文摘要
3D高斯溅射（3DGS）中的语义分割对于推进3D场景理解至关重要。现有方法主要依赖特征蒸馏，这会产生大量的逐场景训练开销，且常导致模糊的分割边界。我们发现，这些边界伪影部分由视角覆盖不足以及各向异性高斯基元的边界溢出导致。为应对这些挑战，我们提出VCAR，一种基于视图完整性和轴感知边界优化的无需训练的由粗到细的分割策略。在粗阶段，基于可见性的加权多视图投票方案可快速定位目标；在细阶段，由粗结果导出的以目标为中心的球体通过球形螺旋采样（SSS）生成补充视角，使增强视角下的多视图投票能精确优化目标边界并抑制无关的3D高斯。此外，我们引入轴感知边界优化（ABR）以缓解各向异性基元带来的伪影，通过将投影的2D协方差分解为各轴贡献，ABR识别导致边界泄漏的主导轴，并仅沿该轴应用针对性的各向异性压缩。在NVOS和LERF上开展的大量实验表明，VCAR无需训练即可达到最先进的分割精度与效率。我们的代码可在该https URL获取。
英文摘要
Semantic segmentation in 3D Gaussian Splatting (3DGS) is crucial for advancing 3D scene understanding. Existing methods predominantly rely on feature distillation, which incurs substantial per-scene training overhead and often yields blurred segmentation boundaries. We identify that these boundary artifacts are driven in part by insufficient viewpoint coverage and boundary overflow of anisotropic Gaussian primitives. To address these challenges, we propose VCAR, a training-free coarse-to-fine segmentation strategy based on View Completeness and Axis-aware Boundary Refinement. In the coarse stage, a visibility-based weighted multi-view voting scheme rapidly localizes the target. In the fine stage, an object-centric sphere derived from the coarse result generates supplementary viewpoints via Spherical Spiral Sampling (SSS), allowing multi-view voting on the augmented views to precisely refine object boundaries and suppress irrelevant 3D Gaussians. Moreover, we introduce Axis-aware Boundary Refinement (ABR) to mitigate artifacts from anisotropic primitives. By decomposing the projected 2D covariance into per-axis contributions, ABR identifies the dominant axis responsible for boundary leakage and applies targeted anisotropic compression exclusively along that axis. Extensive experiments on NVOS and LERF demonstrate that VCAR achieves state-of-the-art segmentation accuracy and efficiency without training. Our code is available at https://github.com/DDKK0526/VCAR.
CommentsAccepted to the 34th ACM International Conference on Multimedia (MM '26). 16 pages, 11 figures, including supplementary material
