发表机构
Peking University; North China Electric Power University; China University of Geosciences（北京大学; 华北电力大学; 中国地质大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有指代3D高斯点云渲染方法局限，提出ZeroSplat框架，通过多视图几何约束将2D视觉语言模型先验提升至3D空间，无需额外特征存储，在广义和单目标场景中显著优于现有方法，且效率高。
AI 中文摘要
3D高斯点云渲染的进展实现了语言引导的场景理解，但现有指代3D高斯点云渲染方法限于单目标查询。为此引入广义指代3D高斯点云分割任务，构建GR-LERF和GR-ScanNet两个新基准。现有方法存在技术瓶颈，提出ZeroSplat框架，通过多视图几何约束将2D视觉语言模型先验提升到3D空间，无需额外特征存储。实验表明ZeroSplat在多场景中显著优于现有方法且效率高。
英文摘要
Recent advancements in 3D Gaussian Splatting (3DGS) have enabled language-guided scene understanding. However, existing Referring 3D Gaussian Splatting (R3DGS) methods are fundamentally restricted to single-target queries. To reflect the ambiguity of real-world instructions, we introduce the Generalized Referring 3D Gaussian Splatting Segmentation (GR3DGS) task, which requires dynamically segmenting an arbitrary number of targets (0, 1, or $N$). To facilitate comprehensive evaluation of this new task, we construct two new benchmarks: GR-LERF and GR-ScanNet. Crucially, existing R3DGS paradigms exhibit fundamental technical bottlenecks that severely limit their performance on the GR3DGS task: they lack intrinsic 3D point-level understanding by operating merely on 2D rendered pixels, and they incur prohibitive computational overhead by requiring per-scene optimization to embed heavy semantic features. To dismantle these bottlenecks, we propose ZeroSplat, a novel training-free and zero-feature framework. ZeroSplat lifts 2D Vision-Language Model (VLM) priors into 3D space through robust multi-view geometric constraints. This strategy enables intrinsic point-level understanding without incurring any additional feature storage. Extensive experiments demonstrate that ZeroSplat significantly outperforms state-of-the-art methods across generalized and single-target scenarios while maintaining exceptional efficiency. Project Page: https://inkmind-ai.github.io/ZeroSplat
CommentsAccepted to ECCV 2026
