发表机构
School of Geospatial Engineering and Science, Sun Yat-sen University; University of Waterloo（中山大学地理空间工程与科学学院; 滑铁卢大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出以决策为中心的LAF框架，将2D到3D基础模型迁移系统拆分为五个算子，通过对161个系统的审计，为3D感知系统的比较、故障诊断与规范提供了表示无关的方法。
AI 中文摘要
将二维基础模型的预测结果迁移至三维分割的方法通常按任务或表示形式分组，这些分组方式掩盖了决定系统在不同视角间是否保持一致性的关键决策：图像证据的定位位置、观测结果何时归为同一实体、语义与粒度冲突的处理方式、哪些信息需要融合，以及哪些状态会留存以供后续查询。我们提出了以决策为中心的框架——Lift, Associate, and Fuse (LAF)，该框架将迁移系统表示为五个算子：Generate、Associate、Reconcile、Fuse和Persist/Query。LAF为持久载体定义了明确的契约，包括其空间支持、语义状态、实体状态、不确定性、来源及支持的操作，并确定了被丢弃证据变为不可恢复的首个阶段。我们将该框架作为结构化审计协议实施，并将其应用至截至2026年8月7日可获取的161个系统，涵盖基于点、场、高斯、对象、图和记忆的载体。在表示、时间、关系和前馈压力测试中，最终确认通过后无需额外分析阶段。所得决策轨迹揭示了四个反复出现的特性：关联不确立实体身份；载体设计同时确定查询接口与修正边界；渲染视图、原生3D和提议级评估不可互换；“无训练”“实时”“开放词汇”和“可泛化”等限定词仅在附加到特定阶段及完整成本台账时才有意义。因此，LAF提供了一种与表示无关的方法，用于比较现有系统、诊断不可逆故障，并为未来智能体指定可修正的三维感知方案。
英文摘要
Methods that transfer predictions from two-dimensional foundation models into three-dimensional segmentation are commonly grouped by task or representation. Those groupings obscure the decisions that determine whether a system remains coherent across views: where image evidence is grounded, when observations become one identity, how semantic and granularity conflicts are handled, which information is fused, and what state survives for later queries. We introduce \textbf{Lift, Associate, and Fuse (LAF)}, a decision-centric framework that represents a transfer system as five operators: \textbf{Generate, Associate, Reconcile, Fuse, and Persist/Query}. LAF defines an explicit contract for the persistent carrier---its spatial support, semantic state, identity state, uncertainty, provenance, and supported operations---and identifies the first stage at which discarded evidence becomes unrecoverable. We operationalize the framework as a structured audit protocol and apply it to 161 systems available through 7 August 2026, spanning point-, field-, Gaussian-, object-, graph-, and memory-based carriers. Representation, temporal, relational, and feed-forward stress tests required no additional analytical stage after the final confirmation pass. The resulting decision traces expose four recurring properties: association does not establish identity; carrier design fixes both the query interface and correction boundary; rendered-view, native-3D, and proposal-level evaluations are not interchangeable; and qualifiers such as \emph{training-free}, \emph{real-time}, \emph{open-vocabulary}, and \emph{generalizable} are meaningful only when attached to a stage and a complete cost ledger. LAF therefore supplies a representation-neutral method for comparing existing systems, diagnosing irreversible failures, and specifying revisable 3D perception for future agents.
CommentsA framework to realize 3D segmentation
