用于可编辑高斯溅射的神经表面先验
Neural Surface Priors for Editable Gaussian Splatting
AI总结：
针对从图像数据恢复可修改场景外观的需求，提出结合3D高斯溅射与隐式表面表示的方法，通过神经符号距离场重建场景表面并作为几何先验指导训练，利用三角形面片代理实现网格编辑传播，支持更广泛修改且充分利用网格拓扑，提升编辑灵活性与直观性。
摘要：
在计算机图形学和视觉领域，从图像数据中恢复易于修改的场景外观对于内容创建等应用至关重要。我们提出一种将3D高斯溅射与隐式表面表示相结合的新方法，通过网格操作实现对恢复场景的直观编辑。从一组输入图像和相机姿态出发，我们的方法利用神经符号距离场重建场景表面。该神经表面作为几何先验，指导高斯溅射组件的训练，确保其与场景几何对齐。为便于编辑，我们将视觉和几何信息编码为轻量级三角形面片代理。对从神经表面提取的网格进行的编辑通过该中间结构无缝传播，以更新恢复的外观。与依赖三角形面片代理表示的现有方法不同，我们的方法支持更广泛的修改，并充分利用网格拓扑，实现更灵活、直观的编辑过程。该项目的完整源代码可在以下网址获取：https://github.com/WJakubowska/NeuralSurfacePriors。
英文摘要：
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.
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。
