用3D高斯点云实现零样本全景分割，区分物体并精准重建。
Split&Splat: Zero-Shot Panoptic Segmentation via Explicit Instance Modeling and 3D Gaussian Splatting
- 先分割场景再独立重建每个物体实例
- 在ScanNetv2上达到当前最优分割性能
- 支持物体检索与三维编辑等下游任务
3D高斯点云（3DGS）可实现快速高质量的场景重建，但缺乏一致的对象结构和语义感知。我们提出Split&Splat，一种基于3DGS的全景场景重建框架。该方法显式建模物体实例：首先利用深度信息跨视角传播实例掩码，生成视图一致的2D掩码；然后独立重建每个物体，并合并回场景同时优化边界；最后在重建物体中嵌入实例级语义描述符，支持全景分割、物体检索与3D编辑等应用。与现有方法不同，Split&Splat采用先分割后重建的设计，自然支持下游任务，并在ScanNetv2分割基准上达到当前最优性能。
原文摘要 · Abstract (English)
3D Gaussian Splatting (GS) enables fast and high-quality scene reconstruction, but it lacks an object-consistent and semantically aware structure. We propose Split&Splat, a framework for panoptic scene reconstruction using 3DGS. Our approach explicitly models object instances. It first propagates instance masks across views using depth, thus producing view-consistent 2D masks. Each object is then reconstructed independently and merged back into the scene while refining its boundaries. Finally, instance-level semantic descriptors are embedded in the reconstructed objects, supporting various applications, including panoptic segmentation, object retrieval, and 3D editing. Unlike existing methods, Split&Splat tackles the problem by first segmenting the scene and then reconstructing each object individually. This design naturally supports downstream tasks and allows Split&Splat to achieve state-of-the-art performance on the ScanNetv2 segmentation benchmark.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。