# SAGOnline: Segment Any Gaussians Online

Source: [SAGOnline: Segment Any Gaussians Online](<https://www.sota2.com/research/paper/68fa7a841e209131cea83a6b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-08T05:00:05.049Z

Authors: Wentao Sun, Quanyun Wu, Hanqing Xu, Kyle Gao, Zhengsen Xu, Yiping Chen, Dedong Zhang, Lingfei Ma, John S. Zelek, Jonathan Li

Published: 2025-08-11T17:38:50.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.08219>)

[PDF](<https://arxiv.org/pdf/2508.08219.pdf>)
