arXiv 2507.049612025-07-07cs.CV

InterGSEdit：基于三维几何一致注意力先验的交互式三维高斯泼溅编辑

InterGSEdit: Interactive 3D Gaussian Splatting Editing with 3D Geometry-Consistent Attention Prior

MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（信息产业部模式分析与机器智能重点实验室，计算机科学与技术学院，南京航空航天大学）；The Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology（教育部高维信息智能感知与系统重点实验室，计算机科学与工程学院，南京理工大学）

Minghao Wen, Shengjie Wu, Kangkan Wang, Dong Liang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出 InterGSEdit 框架，通过交互式关键视图选择、CLIP 语义一致性筛选和三维几何一致注意力先验，结合注意力融合网络，解决三维高斯泼溅多视图编辑中的局部不一致和编辑程度不可控问题，实现高保真三维编辑。

摘要：

近年来，基于三维高斯泼溅（3D Gaussian Splatting）的三维编辑展现出了令人瞩目的性能。然而，多视图编辑常常表现出明显的局部不一致性，尤其是在非刚性变形区域，这会导致编辑后的三维场景出现局部伪影、纹理模糊或语义变化。我们还发现，现有完全依赖文本提示的编辑方法使编辑过程成为“一次性操作”，用户难以灵活控制编辑程度。针对这些挑战，我们提出了 InterGSEdit，这是一个通过交互式选择符合用户偏好的关键视图来实现高质量三维高斯泼溅编辑的新框架。我们提出了一种基于 CLIP 的语义一致性选择（CSCS）策略，为每个用户选择的关键视图自适应地筛选一组语义一致的参考视图。然后，利用从参考视图导出的交叉注意力图，通过加权高斯泼溅反投影构建三维几何一致注意力先验（$GAP^{3D}$）。我们将 $GAP^{3D}$ 投影以获得三维约束注意力，并通过注意力融合网络（AFN）将其与二维交叉注意力融合。AFN 采用自适应注意力策略，在推理早期优先使用三维约束注意力以保证几何一致性，并在推理后期逐渐优先使用扩散中的二维交叉注意力图以获取细粒度特征。大量实验表明，InterGSEdit 达到了最先进的性能，能够提供一致、高保真的三维高斯泼溅编辑，并改善了用户体验。

英文摘要：

3D Gaussian Splatting based 3D editing has demonstrated impressive performance in recent years. However, the multi-view editing often exhibits significant local inconsistency, especially in areas of non-rigid deformation, which lead to local artifacts, texture blurring, or semantic variations in edited 3D scenes. We also found that the existing editing methods, which rely entirely on text prompts make the editing process a "one-shot deal", making it difficult for users to control the editing degree flexibly. In response to these challenges, we present InterGSEdit, a novel framework for high-quality 3DGS editing via interactively selecting key views with users' preferences. We propose a CLIP-based Semantic Consistency Selection (CSCS) strategy to adaptively screen a group of semantically consistent reference views for each user-selected key view. Then, the cross-attention maps derived from the reference views are used in a weighted Gaussian Splatting unprojection to construct the 3D Geometry-Consistent Attention Prior ($GAP^{3D}$). We project $GAP^{3D}$ to obtain 3D-constrained attention, which are fused with 2D cross-attention via Attention Fusion Network (AFN). AFN employs an adaptive attention strategy that prioritizes 3D-constrained attention for geometric consistency during early inference, and gradually prioritizes 2D cross-attention maps in diffusion for fine-grained features during the later inference. Extensive experiments demonstrate that InterGSEdit achieves state-of-the-art performance, delivering consistent, high-fidelity 3DGS editing with improved user experience.

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。

AI总结：

摘要：

英文摘要：

相关论文