Saved in:
Bibliographic Details
Main Authors: Sun, Wentao, Wu, Quanyun, Xu, Hanqing, Gao, Kyle, Xu, Zhengsen, Chen, Yiping, Zhang, Dedong, Ma, Lingfei, Zelek, John S., Li, Jonathan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.08219
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911356738863104
author Sun, Wentao
Wu, Quanyun
Xu, Hanqing
Gao, Kyle
Xu, Zhengsen
Chen, Yiping
Zhang, Dedong
Ma, Lingfei
Zelek, John S.
Li, Jonathan
author_facet Sun, Wentao
Wu, Quanyun
Xu, Hanqing
Gao, Kyle
Xu, Zhengsen
Chen, Yiping
Zhang, Dedong
Ma, Lingfei
Zelek, John S.
Li, Jonathan
contents 3D Gaussian Splatting has emerged as a powerful paradigm for explicit 3D scene representation, yet achieving efficient and consistent 3D segmentation remains challenging. Existing segmentation approaches typically rely on high-dimensional feature lifting, which causes costly optimization, implicit semantics, and task-specific constraints. We present \textbf{Segment Any Gaussians Online (SAGOnline)}, a unified, zero-shot framework that achieves real-time, cross-view consistent segmentation without scene-specific training. SAGOnline decouples the monolithic segmentation problem into lightweight sub-tasks. By integrating video foundation models (e.g., SAM 2), we first generate temporally consistent 2D masks across rendered views. Crucially, instead of learning continuous feature fields, we introduce a \textbf{Rasterization-aware Geometric Consensus} mechanism that leverages the traceability of the Gaussian rasterization pipeline. This allows us to deterministically map 2D predictions to explicit, discrete 3D primitive labels in real-time. This discrete representation eliminates the memory and computational burden of feature distillation, enabling instant inference. Extensive evaluations on NVOS and SPIn-NeRF benchmarks demonstrate that SAGOnline achieves state-of-the-art accuracy (92.7\% and 95.2\% mIoU) while operating at the fastest speed at 27 ms per frame. By providing a flexible interface for diverse foundation models, our framework supports instant prompt, instance, and semantic segmentation, paving the way for interactive 3D understanding in AR/VR and robotics.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08219
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SAGOnline: Segment Any Gaussians Online
Sun, Wentao
Wu, Quanyun
Xu, Hanqing
Gao, Kyle
Xu, Zhengsen
Chen, Yiping
Zhang, Dedong
Ma, Lingfei
Zelek, John S.
Li, Jonathan
Computer Vision and Pattern Recognition
3D Gaussian Splatting has emerged as a powerful paradigm for explicit 3D scene representation, yet achieving efficient and consistent 3D segmentation remains challenging. Existing segmentation approaches typically rely on high-dimensional feature lifting, which causes costly optimization, implicit semantics, and task-specific constraints. We present \textbf{Segment Any Gaussians Online (SAGOnline)}, a unified, zero-shot framework that achieves real-time, cross-view consistent segmentation without scene-specific training. SAGOnline decouples the monolithic segmentation problem into lightweight sub-tasks. By integrating video foundation models (e.g., SAM 2), we first generate temporally consistent 2D masks across rendered views. Crucially, instead of learning continuous feature fields, we introduce a \textbf{Rasterization-aware Geometric Consensus} mechanism that leverages the traceability of the Gaussian rasterization pipeline. This allows us to deterministically map 2D predictions to explicit, discrete 3D primitive labels in real-time. This discrete representation eliminates the memory and computational burden of feature distillation, enabling instant inference. Extensive evaluations on NVOS and SPIn-NeRF benchmarks demonstrate that SAGOnline achieves state-of-the-art accuracy (92.7\% and 95.2\% mIoU) while operating at the fastest speed at 27 ms per frame. By providing a flexible interface for diverse foundation models, our framework supports instant prompt, instance, and semantic segmentation, paving the way for interactive 3D understanding in AR/VR and robotics.
title SAGOnline: Segment Any Gaussians Online
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.08219