用变形笼控制3D高斯点云，保持细节的同时实现任意形状变形。
CAGE-GS: High-fidelity Cage Based 3D Gaussian Splatting Deformation
- 基于目标形状构建变形笼，引导源场景几何变化。
- 通过雅可比矩阵更新协方差参数，有效保留纹理细节。
- 支持文本、图像、网格等多种输入，适用性强。
随着3D高斯点云（3DGS）在真实场景表示中的流行，如何在保持原始细节的前提下实现用户友好的场景变形成为研究热点。本文提出CAGE-GS，一种基于变形笼的3DGS变形方法，能将源3DGS场景与用户定义的目标形状无缝对齐。该方法从目标形状学习一个变形笼，指导源场景的几何变换。尽管变形笼能有效控制结构对齐，但因协方差参数复杂，保持纹理外观仍具挑战。为此，我们采用基于雅可比矩阵的策略更新每个高斯点的协方差参数，确保变形后纹理保真度。本方法高度灵活，可适配文本、图像、点云、网格及3DGS模型等多种目标形状表示。在公开数据集和新构建场景上的大量实验与消融研究显示，其在效率和变形质量上显著优于现有方法。
原文摘要 · Abstract (English)
As 3D Gaussian Splatting (3DGS) gains popularity as a 3D representation of real scenes, enabling user-friendly deformation to create novel scenes while preserving fine details from the original 3DGS has attracted significant research attention. We introduce CAGE-GS, a cage-based 3DGS deformation method that seamlessly aligns a source 3DGS scene with a user-defined target shape. Our approach learns a deformation cage from the target, which guides the geometric transformation of the source scene. While the cages effectively control structural alignment, preserving the textural appearance of 3DGS remains challenging due to the complexity of covariance parameters. To address this, we employ a Jacobian matrix-based strategy to update the covariance parameters of each Gaussian, ensuring texture fidelity post-deformation. Our method is highly flexible, accommodating various target shape representations, including texts, images, point clouds, meshes and 3DGS models. Extensive experiments and ablation studies on both public datasets and newly proposed scenes demonstrate that our method significantly outperforms existing techniques in both efficiency and deformation quality.
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。