VCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary Refinement
2026-08-31 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address problems in segmenting 3D scenes represented by Gaussian splatting, where existing methods are slow and produce blurry edges. They propose VCAR, a technique that refines object boundaries using a two-step process without any training. First, it uses multiple views to find the object roughly, then adds more viewpoints around the object to improve the boundary clarity. They also fix boundary errors caused by stretched Gaussian shapes by adjusting them along specific directions. Their experiments show better and faster results than previous methods.
3D Gaussian SplattingSemantic SegmentationMulti-view VotingAnisotropic Gaussian PrimitivesBoundary RefinementSpherical Spiral SamplingVisibility-based WeightingCovariance DecompositionTraining-free Segmentation
Authors
Kun Cao, Di Wang, Haibin Zhu, Haozhi Huang, Xu Wang, Zheng Shi, Guanghua Yang
Abstract
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.