一致实例场：面向动态场景理解
Consistent Instance Field for Dynamic Scene Understanding
将实例身份与可见性解耦，用可变形3D高斯联合编码辐射与语义，并通过可微光栅化从RGB和掩码直接学习，为动态场景的新视角全景分割和开放词表4D查询提供了连续概率表示方案。
原文依据 instance-embedded representation based on deformable 3D Gaussians, which jointly encode radiance and semantic information
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出一致实例场，一种用于动态场景理解的连续概率时空表示。与依赖离散跟踪或视角相关特征的先前方法不同，我们的方法通过用占用概率和条件实例分布对每个时空点建模，将可见性与持久对象身份解耦。为实现这一点，我们引入一种基于可变形3D高斯的新型实例嵌入表示，该表示联合编码辐射和语义信息，并通过可微光栅化直接从输入RGB图像和实例掩码中学习。此外，我们引入新机制来校准每个高斯的身份，并重新采样高斯以朝向语义活跃区域，确保跨空间和时间的一致实例表示。在HyperNeRF和Neu3D数据集上的实验表明，我们的方法在新视角全景分割和开放词表4D查询任务上显著优于最优方法。
英文原文摘要 1053 字符
We introduce Consistent Instance Field, a continuous and probabilistic spatio-temporal representation for dynamic scene understanding.Unlike prior methods that rely on discrete tracking or view-dependent features, our approach disentangles visibility from persistent object identity by modeling each space-time point with an occupancy probability and a conditional instance distribution. To realize this, we introduce a novel instance-embedded representation based on deformable 3D Gaussians, which jointly encode radiance and semantic information and are learned directly from input RGB images and instance masks through differentiable rasterization.Furthermore, we introduce new mechanisms to calibrate per-Gaussian identities and resample Gaussians toward semantically active regions, ensuring consistent instance representations across space and time. Experiments on HyperNeRF and Neu3D datasets demonstrate that our method significantly outperforms state-of-the-art methods on novel-view panoptic segmentation and open-vocabulary 4D querying tasks.