用户画轮廓就能精准变形3D高斯点云，支持动画生成。
Sketch-guided Cage-based 3D Gaussian Splatting Deformation
- 用草图+笼形变形+神经雅可比场实现精细几何调整
- 结合2D扩散模型与ControlNet确保变形语义合理
- 适合需要直观编辑3D模型的创作者和动画师
3D高斯点云（3D Gaussian Splatting, GS）是计算机图形学与视觉领域备受关注的新型3D表示方法。尽管已有系统引入了文本引导等编辑能力，但对几何变形的细粒度控制仍具挑战。本文提出一种新型草图引导的3D GS变形系统，用户仅需从单视角绘制轮廓草图，即可直观修改3D GS模型的几何结构。该方法结合笼形变形与神经雅可比场变体，实现精确、细粒度的控制；同时利用大规模2D扩散先验与ControlNet，确保生成变形在语义上合理。实验验证了方法的有效性，并展示了其将静态3D GS模型动画化的核心应用能力。
原文摘要 · Abstract (English)
3D Gaussian Splatting (GS) is one of the most promising novel 3D representations that has received great interest in computer graphics and computer vision. While various systems have introduced editing capabilities for 3D GS, such as those guided by text prompts, fine-grained control over deformation remains an open challenge. In this work, we present a novel sketch-guided 3D GS deformation system that allows users to intuitively modify the geometry of a 3D GS model by drawing a silhouette sketch from a single viewpoint. Our approach introduces a new deformation method that combines cage-based deformations with a variant of Neural Jacobian Fields, enabling precise, fine-grained control. Additionally, it leverages large-scale 2D diffusion priors and ControlNet to ensure the generated deformations are semantically plausible. Through a series of experiments, we demonstrate the effectiveness of our method and showcase its ability to animate static 3D GS models as one of its key applications.
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。