LangField4D：为动态场景学习身份自适应且时空连续的 4D 语言场
LangField4D: Learning Identity-Adaptive and Spatio-Temporal Continuous 4D Language Fields for Dynamic Scenes
把 4D 高斯与连续三平面语义场结合，用可学习身份自适应特征解决运动场跨物体边界导致的语义振荡，可直接复用于动态场景的开放词表分割与跟踪。
原文依据 we propose LangField4D, a novel 4D Gaussian framework that jointly models spatio-temporal identity and semantics
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论构建支持开放词表查询的 4D 语言场，对于动态环境中的语义感知与交互至关重要。现有的基于 4D 高斯的方法面临两大挑战。第一，每个高斯具有静态身份的假设会导致语义不一致：运动场会随时间使高斯跨越物体边界发生形变，从而引起身份分配的振荡。第二，现有方法通常将动态语义建模为一组离散的、预定义的状态原型，无法刻画动态连续性，也难以划分细粒度的时序边界。为解决这些问题，我们提出 LangField4D，一种新颖的 4D 高斯框架，在统一且连续的表示中联合建模时空身份与语义。我们引入身份自适应高斯分组模块，为每个高斯分配一个可学习的自适应特征，以动态捕捉其物体归属，从而保证跨时间的语义跟踪一致性。基于该归属结构，我们进一步设计了基于三平面表示的连续时空语义学习机制，在连续潜变量空间中编码时不变语义与时变语义。在动态场景基准上的大量实验表明，我们在时间无关与时间敏感的开放词表查询任务上均取得了最优性能。
英文原文摘要 1434 字符
Constructing a 4D language field that supports open-vocabulary queries is essential for semantic perception and interaction in dynamic environments. Existing 4D Gaussian-based approaches face two major challenges. First, the assumption of a static identity per Gaussian leads to semantic inconsistency, as motion fields warp Gaussians across object boundaries over time, causing oscillating identity assignments. Second, current methods typically model dynamic semantics as a set of discrete, predefined state prototypes, which fail to capture dynamic continuity and delineate fine-grained temporal boundaries. To address these issues, we propose LangField4D, a novel 4D Gaussian framework that jointly models spatio-temporal identity and semantics in a unified and continuous representation. We introduce an Identity-Adaptive Gaussian Grouping module that assigns each Gaussian a learnable adaptation feature to dynamically capture its object affiliation, ensuring consistent semantic tracking across time. Building upon this affiliation structure, we further design a Continuous Spatio-Temporal Semantic Learning mechanism based on a Tetraplane representation, which encodes both time-invariant and time-varying semantics within a continuous latent space. Extensive experiments on dynamic scene benchmarks demonstrate that we achieve state-of-the-art performance on both time-agnostic and time-sensitive open-vocabulary query tasks.