AG$^2$aussian：基于锚点图结构的高斯泼溅用于实例级3D场景理解与编辑
AG$^2$aussian: Anchor-Graph Structured Gaussian Splatting for Instance-Level 3D Scene Understanding and Editing
AI总结：
本文提出AG$^2$aussian框架，利用锚点图结构组织语义特征并规范高斯基元，实现干净准确的实例级高斯选择，在交互查询、开放词汇查询、物体移除和物理模拟等应用中展现出优势。
摘要：
3D高斯泼溅（3DGS）已在各种应用中呈指数级普及，这推动了对语义感知的3D高斯表示的关键需求，以支持场景理解和编辑任务。现有方法通常将语义特征附加到一组自由高斯上，并通过可微渲染来蒸馏这些特征，这导致分割结果嘈杂且高斯选择混乱。在本文中，我们提出了AG$^2$aussian，一种新颖的框架，利用锚点图结构来组织语义特征并规范高斯基元。我们的锚点图结构不仅促进了紧凑且实例感知的高斯分布，还便于基于图的传播，实现了干净且准确的实例级高斯选择。在四个应用（即交互式点击查询、开放词汇文本驱动查询、物体移除编辑和物理模拟）中的广泛验证证明了我们方法的优势及其对各种应用的益处。实验和消融研究进一步评估了我们方法关键设计的有效性。
英文摘要：
3D Gaussian Splatting (3DGS) has witnessed exponential adoption across diverse applications, driving a critical need for semantic-aware 3D Gaussian representations to enable scene understanding and editing tasks. Existing approaches typically attach semantic features to a collection of free Gaussians and distill the features via differentiable rendering, leading to noisy segmentation and a messy selection of Gaussians. In this paper, we introduce AG$^2$aussian, a novel framework that leverages an anchor-graph structure to organize semantic features and regulate Gaussian primitives. Our anchor-graph structure not only promotes compact and instance-aware Gaussian distributions, but also facilitates graph-based propagation, achieving a clean and accurate instance-level Gaussian selection. Extensive validation across four applications, i.e. interactive click-based query, open-vocabulary text-driven query, object removal editing, and physics simulation, demonstrates the advantages of our approach and its benefits to various applications. The experiments and ablation studies further evaluate the effectiveness of the key designs of our approach.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
