MORE-STEM：面向查询驱动3D/4D点云分割的长短期记忆召回与时空一致性模型
MORE-STEM: Long-Short MemOry REcall and Spatio-TEmporal Consistency Model for Query-Driven 3D/4D Point Cloud Segmentation
面向动态点云的查询驱动分割，其跨帧文本-视觉对齐与时空一致性约束可直接迁移到4D点云序列的开放词表/指令分割任务，长短期记忆模块为跨场景推理提供可复用的分层记忆设计。
原文依据 a unified framework for Long-Short MemOry REcall and Spatio-TEmporal Consistency Model in Query-Driven 3D/4D Point Cloud Segmentation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当前查询驱动的三维理解方法局限于静态点云，限制了其对动态场景进行推理的能力。为弥补这一空白，我们提出 MORE-STEM，一个面向查询驱动3D/4D点云分割的长短期记忆召回与时空一致性模型的统一框架。该框架首先引入跨帧文本-视觉对齐模块，在语言查询与动态三维特征之间建立细粒度、时间感知的对应关系。在此基础上，时空一致性模型模块在连续帧之间施加运动感知的连贯性约束，确保分割结果稳定且时间一致。长短期记忆召回模块进一步通过分层记忆增强跨场景推理能力，在长期语义召回与短期自适应之间取得平衡。我们还构建了一个新的室外基准，用于3D与4D指令分割，配有在时间上对齐、以运动为中心的文本标注。实验表明，MORE-STEM 在多个3D与4D理解任务上取得了最优性能。
英文原文摘要 1113 字符
Current query-driven 3D understanding methods are constrained to static point clouds, limiting their ability to reason about dynamic scenes. To bridge this gap, we propose MORE-STEM, a unified framework for Long-Short MemOry REcall and Spatio-TEmporal Consistency Model in Query-Driven 3D/4D Point Cloud Segmentation. The framework first introduces a Cross-Frame Text-Visual Alignment module that establishes fine-grained, time-aware correspondences between linguistic queries and dynamic 3D features. Building on this, a Spatio-Temporal Consistency Model module enforces motion-aware coherence across consecutive frames, ensuring stable and temporally consistent segmentation. A Long-Short Memory Recall module further enhances cross-scene reasoning through hierarchical memory that balances long-term semantic recall and short-term adaptation. We also construct a new outdoor benchmark for both 3D and 4D instruction segmentation with temporally aligned, motion-centric text annotations. Experiments demonstrate that MORE-STEM achieves state-of-the-art performance across multiple 3D and 4D understanding tasks.