Metraipolis › archive › dc_a32389569dfd

VCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary Refinement — arXiv:2608.30870

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.30870
License (as archived): CC0-1.0
Archived: 2026-10-17T09:59:44.087Z
SHA-256 of the archived text: 429df072ea71fe6f7b4330f0728d8648eadd72da89f56c6fe3e2b3a2cabb5ac1
Stable URL of this page: https://metraipolis.com/documento/dc_a32389569dfd

How to cite

VCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary Refinement — arXiv:2608.30870 — arXiv (en), https://arxiv.org/abs/2608.30870 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a32389569dfd (Metraipolis archive dc_a32389569dfd, sha256 429df072ea71fe6f7b4330f0728d8648eadd72da89f56c6fe3e2b3a2cabb5ac1)

BibTeX

@misc{dca32389569dfd,
  title = {VCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary Refinement — arXiv:2608.30870},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30870},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a32389569dfd; sha256 429df072ea71fe6f7b4330f0728d8648eadd72da89f56c6fe3e2b3a2cabb5ac1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30870. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.30870 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T09:28:48.195Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).