发表机构
Southern University of Science and Technology; ByteDance; Zhejiang University; Fudan University; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（南方科技大学; 字节跳动; 浙江大学; 复旦大学; 中国科学院深圳先进技术研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对3D场景多物体移除的挑战，提出CoGeo-GS框架，通过概念感知语义标签与几何感知补全流水线实现可控多物体移除，在视觉质量与重建保真度上优于现有方法。
AI 中文摘要
3D场景中的多物体移除任务极具挑战性，原因在于存在严重遮挡、语义纠缠，且难以维持几何与多视图一致性。现有3D高斯溅射（3DGS）方法在单物体编辑中表现良好，但扩展至多物体场景时性能不佳，常需重复优化且在移除区域生成不稳定几何结构。我们提出CoGeo-GS，这是一种用于3D场景可控多物体移除的概念驱动框架。CoGeo-GS为高斯分配概念感知语义标签，支持灵活的物体选择，并在单一优化阶段减少前景物体与背景结构间的干扰。为恢复合理几何结构，我们引入几何感知补全流水线，结合单目深度先验、基于扩散的细化及边界对齐融合；几何正则化细化策略进一步稳定重建并保留多视图一致性。实验表明，CoGeo-GS在视觉质量与重建保真度上优于现有方法。
英文摘要
Multi-object removal in 3D scenes is challenging due to severe occlusions, semantic entanglement, and the difficulty of maintaining geometric and multi-view consistency. Existing 3D Gaussian Splatting (3DGS) methods perform well for single-object editing but scale poorly to multi-object scenarios, often requiring repetitive optimization and yielding unstable geometry in removed regions. We propose CoGeo-GS, a concept-driven framework for controllable multi-object removal in 3D scenes. CoGeo-GS assigns concept-aware semantic tags to Gaussians, enabling flexible object selection and reducing interference between foreground objects and background structures within a single optimization stage. To recover plausible geometry, we introduce a geometry-aware completion pipeline that combines monocular depth priors with diffusion-based refinement and boundary-aligned blending. A geometry-regularized refinement strategy further stabilizes reconstruction and preserves multi-view consistency. Experiments demonstrate that CoGeo-GS outperforms existing methods in visual quality and reconstruction fidelity.
Comments6 pages, 4 figures, accepted at ICME 2026
