B^3-Seg：基于解析期望信息增益与Beta-Bernoulli贝叶斯更新的无相机、免训练3DGS分割
B$^3$-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta-Bernoulli Bayesian Updates
提出一种无需相机位姿和训练、基于贝叶斯更新与解析期望信息增益的主动视角选择策略，可复用于3DGS场景的开放词表分割与交互式编辑，为低延迟3D资产处理提供理论保证的采样方案。
原文依据 actively selects the next view via analytic Expected Information Gain (EIG)
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论交互式3D高斯泼溅（3DGS）分割对于影视和游戏制作中预重建资产的实时编辑至关重要。然而，现有方法依赖预定义的相机视角、真实标签或昂贵的重新训练，使其难以适用于低延迟场景。我们提出B^3-Seg（面向3DGS的Beta-Bernoulli贝叶斯分割），一种在无相机、免训练条件下实现开放词表3DGS分割的快速且具有理论依据的方法。该方法将分割重新表述为序列化的Beta-Bernoulli贝叶斯更新，并通过解析期望信息增益（EIG）主动选择下一个视角。这种贝叶斯形式保证了EIG的自适应单调性和子模性，从而产生对最优视角采样策略的贪心（1-1/e）近似。在多个数据集上的实验表明，B^3-Seg在数秒内完成端到端分割，同时取得与高成本监督方法相竞争的结果。结果表明，B^3-Seg能够实现具有可证明信息效率的实用交互式3DGS分割。
英文原文摘要 1123 字符
Interactive 3D Gaussian Splatting (3DGS) segmentation is essential for real-time editing of pre-reconstructed assets in film and game production.However, existing methods rely on predefined camera viewpoints, ground-truth labels, or costly retraining, making them impractical for low-latency use.We propose B^3-Seg (Beta--Bernoulli Bayesian Segmentation for 3DGS), a fast and theoretically grounded method for open-vocabulary 3DGS segmentation under camera-free and training-free conditions.Our approach reformulates segmentation as sequential Beta-Bernoulli Bayesian updates and actively selects the next view via analytic Expected Information Gain (EIG).This Bayesian formulation guarantees the adaptive monotonicity and submodularity of EIG, which produces a greedy (1-1/e) approximation to the optimal view sampling policy.Experiments on multiple datasets show that B^3-Seg achieves competitive results to high-cost supervised methods while operating end-to-end segmentation within a few seconds.The results demonstrate that B^3-Seg enables practical, interactive 3DGS segmentation with provable information efficiency.