场景即对象，而非基元：来自无位姿视图的实例结构化3D令牌化

摘要

3D场景是通过其中的物体来理解的，而非组成物体的基元。然而，前馈式重建方法输出的是密集、无结构的点集或高斯体，物体级结构只能事后恢复。我们提出了一种前馈框架，直接从无位姿的多视图图像中，将场景分解为具有实例结构的3D令牌组——这些紧凑的以对象为中心单元，使得重建、分割和操作都能随之进行。每个令牌组将一个捕获实体级身份的实例令牌与编码局部几何和外观的锚定令牌配对，并解码为一组3D高斯体。这种双层因子分解将物体身份与局部外观解耦，使得物体实例成为表示的原生接口，而非派生产物。令牌组通过联合重建与分割监督的可微渲染进行学习，无需3D标注。我们的前馈模型在类别无关的实例分割上超越了逐场景优化基线，同时在新视角合成方面保持竞争力。除了这些指标之外，相同的令牌组可直接实现实例级场景编辑——通过操作对应的组来移除、平移或插入物体——以及高效的开放词汇3D实例检索，其检索复杂度随实例数量而非基元数量扩展。

English

A 3D scene is understood through its objects, not the primitives that compose them. Yet feed-forward reconstruction methods output dense, unstructured sets of points or Gaussians, leaving object-level structure to be recovered after the fact. We propose a feed-forward framework that decomposes a scene into instance-structured 3D token groups directly from unposed multi-view images -- compact object-centric units from which reconstruction, segmentation, and manipulation all follow. Each token group pairs an instance token capturing entity-level identity with anchor tokens that encode local geometry and appearance, which are decoded into a set of 3D Gaussians. This two-level factorization decouples object identity from local appearance, making object instances a native interface of the representation rather than a derived product. The token groups are learned through differentiable rendering with joint reconstruction and segmentation supervision, requiring no 3D annotations. Our feed-forward model surpasses per-scene optimization baselines in class-agnostic instance segmentation while remaining competitive in novel view synthesis. Beyond these metrics, the same token groups directly unlock instance-level scene editing -- removing, translating, or inserting objects by operating on their groups -- as well as efficient open-vocabulary 3D instance retrieval, where retrieval complexity scales with the number of instances rather than primitives.