用神经表面先验让高斯点云可编辑，支持灵活修改场景外观。
Neural Surface Priors for Editable Gaussian Splatting
- 用神经符号距离场构建几何先验，指导高斯点云对齐场景
- 通过轻量三角面片代理实现编辑结果无缝传播
- 支持多种修改操作，适合内容创作与交互式编辑
在计算机图形学与视觉领域，从图像数据中恢复可轻松修改的场景外观对内容创作等应用至关重要。本文提出一种新方法，将3D高斯点云与隐式表面表示结合，通过网格操作实现对重建场景的直观编辑。给定输入图像与相机位姿，方法首先利用神经符号距离场重建场景表面，该表面作为几何先验，指导高斯点云组件的训练，确保其与场景几何一致。为支持编辑，将视觉与几何信息编码为轻量级三角面片代理。对神经表面提取的网格施加的编辑可通过此中间结构无缝传递，更新恢复的外观。相比以往依赖三角面片代理的方法，本方法支持更广泛的修改类型，充分挖掘网格拓扑潜力，实现更灵活、直观的编辑体验。完整代码见：https://github.com/WJakubowska/NeuralSurfacePriors。
原文摘要 · Abstract (English)
In computer graphics and vision, recovering easily modifiable scene appearance from image data is crucial for applications such as content creation. We introduce a novel method that integrates 3D Gaussian Splatting with an implicit surface representation, enabling intuitive editing of recovered scenes through mesh manipulation. Starting with a set of input images and camera poses, our approach reconstructs the scene surface using a neural signed distance field. This neural surface acts as a geometric prior guiding the training of Gaussian Splatting components, ensuring their alignment with the scene geometry. To facilitate editing, we encode the visual and geometric information into a lightweight triangle soup proxy. Edits applied to the mesh extracted from the neural surface propagate seamlessly through this intermediate structure to update the recovered appearance. Unlike previous methods relying on the triangle soup proxy representation, our approach supports a wider range of modifications and fully leverages the mesh topology, enabling a more flexible and intuitive editing process. The complete source code for this project can be accessed at: https://github.com/WJakubowska/NeuralSurfacePriors.
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。