基于单张图像的3D高斯编辑
3D Gaussian Editing with A Single Image
AI总结：
该研究提出一种基于3D Gaussian Splatting的单图像驱动3D场景编辑方法，通过位置损失、锚点结构与粗到精优化、自适应掩码策略，实现长距离与非刚性形变编辑，效果优于现有方法。
摘要：
对真实世界采集的3D场景进行建模与操作是诸多应用中的核心问题，吸引了越来越多的研究关注。以往的编辑工作通过操控3D网格取得了不错的效果，但这类方法通常需要精准重建的网格才能开展编辑，限制了其在3D内容生成中的应用。为填补这一空白，我们提出了一种基于3D Gaussian Splatting（3D高斯溅射）的新型单图像驱动3D场景编辑方法，可通过直接编辑2D图像平面上的内容实现直观操控。我们的方法通过优化3D高斯，使其与从原始场景用户指定视角渲染的图像的编辑版本对齐。为捕捉长距离物体形变，我们在3D Gaussian Splatting的优化过程中引入位置损失，并通过重参数化实现梯度传播。为处理指定视角渲染时被遮挡的3D高斯，我们构建了基于锚点的结构，并采用由粗到精的优化策略，既能处理长距离形变，又能维持结构稳定性。此外，我们设计了一种新型掩码策略，可自适应识别非刚性形变区域以进行精细建模。大量实验表明，我们的方法在处理几何细节、长距离形变和非刚性形变方面均具有效性，与现有方法相比展现出更优的编辑灵活性与质量。
英文摘要：
The modeling and manipulation of 3D scenes captured from the real world are pivotal in various applications, attracting growing research interest. While previous works on editing have achieved interesting results through manipulating 3D meshes, they often require accurately reconstructed meshes to perform editing, which limits their application in 3D content generation. To address this gap, we introduce a novel single-image-driven 3D scene editing approach based on 3D Gaussian Splatting, enabling intuitive manipulation via directly editing the content on a 2D image plane. Our method learns to optimize the 3D Gaussians to align with an edited version of the image rendered from a user-specified viewpoint of the original scene. To capture long-range object deformation, we introduce positional loss into the optimization process of 3D Gaussian Splatting and enable gradient propagation through reparameterization. To handle occluded 3D Gaussians when rendering from the specified viewpoint, we build an anchor-based structure and employ a coarse-to-fine optimization strategy capable of handling long-range deformation while maintaining structural stability. Furthermore, we design a novel masking strategy to adaptively identify non-rigid deformation regions for fine-scale modeling. Extensive experiments show the effectiveness of our method in handling geometric details, long-range, and non-rigid deformation, demonstrating superior editing flexibility and quality compared to previous approaches.
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。
