发表机构
Simon Fraser University; Google DeepMind; Alberta Machine Intelligence Institute (Amii); Canadian Institute for Advanced Research (CIFAR)（西蒙菲莎大学; 谷歌DeepMind; 阿尔伯塔机器智能研究所; 加拿大高级研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PointGT是一种基于点的三维表示，结合适合几何变形的点表示与学习型UV映射技术，可实现几何与纹理的同步细粒度编辑，且渲染质量高。
AI 中文摘要
我们提出了PointGT，这是一种基于点的三维表示，可实现物体几何与外观的同步编辑。现有重建和视图合成技术生成的体积三维表示质量高、照片级真实感，但难以编辑。特别是，近期为三维高斯溅射（3D Gaussian Splatting）表示实现纹理编辑的工作，无法兼容几何编辑与变形。我们的方法结合了适合几何变形的基于点的表示，以及能实现高分辨率纹理编辑的学习型UV映射技术。结果表明，PointGT可在基于点的神经表示中对几何和纹理进行细粒度编辑，同时保持高渲染质量。
英文摘要
We present PointGT, a point-based 3D representation that enables simultaneous editing of object geometry and appearance. Existing reconstruction and view synthesis techniques produce volumetric 3D representations that are high-quality and photorealistic, but are difficult to edit. In particular, recent efforts to enable texture editing for 3D Gaussian Splatting representations are not compatible with geometry edits and deformations. Our method combines a point-based representation that is well-suited for geometry deformations with a learned UV mapping technique that enables high-resolution texture editing. We show that PointGT enables fine-grained editing of both geometry and texture in point-based neural representations with high rendering quality.
CommentsAccepted to ECCV 2026. Project page: https://zvict.github.io/pointgt/
