实时变化：基于多视角融合的在线场景变化检测
Changes in Real Time: Online Scene Change Detection with Multi-View Fusion
将 3D 高斯泼溅作为在线场景表示，配合 PnP 快速位姿估计与变化引导的增量更新，为视觉研究者提供了一套可复用的「在线、位姿无关、多视角一致」的 3D 场景变化检测框架，可直接迁移到机器人探索、AR 与长期建图等需要实时更新的任务。
原文依据 a fast change-guided update strategy for the 3D Gaussian Splatting scene representation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在线场景变化检测（SCD）是一个极具挑战性的问题，要求智能体在从不受约束的视角观察场景的同时，实时检测相关变化。现有在线 SCD 方法的精度显著低于离线方法。我们提出了首个位姿无关、无需标注并保证多视角一致性的在线 SCD 方法，其运行速度超过 10 FPS，并取得了新的最优性能，甚至超越了最佳的离线方法。我们的方法引入了一种新的自监督融合损失，以从多种线索与观测中推断场景变化；引入基于 PnP 的针对参考场景的快速姿态估计；以及一种面向 3D 高斯泼溅场景表示的快速变化引导更新策略。在复杂真实世界数据集上的大量实验表明，我们的方法优于在线与离线基线。
英文原文摘要 909 字符
Online Scene Change Detection (SCD) is an extremely challenging problem that requires an agent to detect relevant changes on the fly while observing the scene from unconstrained viewpoints. Existing online SCD methods are significantly less accurate than offline approaches. We present the first online SCD approach that is pose-agnostic, label-free, and ensures multi-view consistency, while operating at over 10 FPS and achieving new state-of-the-art performance, surpassing even the best offline approaches. Our method introduces a new self-supervised fusion loss to infer scene changes from multiple cues and observations, PnP-based fast pose estimation against the reference scene, and a fast change-guided update strategy for the 3D Gaussian Splatting scene representation. Extensive experiments on complex real-world datasets demonstrate that our approach outperforms both online and offline baselines.