用深度引导跨视角一致性，实现3D高斯补全的纹理几何统一
3D Gaussian Inpainting with Depth-Guided Cross-View Consistency
- 基于各视角渲染深度，动态更新补全掩码
- 在多个基准数据集上超越现有最先进方法
- 适合需要跨视角一致性的3D内容修复任务
使用NeRF或3D高斯点阵（3DGS）等新视角渲染方法进行3D补全时，如何保证不同视角间的纹理与几何一致性仍是难题。本文提出深度引导跨视角一致性3D高斯补全框架（3DGIC）。通过利用每个训练视角的渲染深度信息，3DGIC识别并利用多视角可见的背景像素来更新补全掩码，从而优化3DGS以适应补全需求。在多个基准数据集上的大量实验表明，3DGIC在定量和定性上均优于当前最先进的3D补全方法。
原文摘要 · Abstract (English)
When performing 3D inpainting using novel-view rendering methods like Neural Radiance Field (NeRF) or 3D Gaussian Splatting (3DGS), how to achieve texture and geometry consistency across camera views has been a challenge. In this paper, we propose a framework of 3D Gaussian Inpainting with Depth-Guided Cross-View Consistency (3DGIC) for cross-view consistent 3D inpainting. Guided by the rendered depth information from each training view, our 3DGIC exploits background pixels visible across different views for updating the inpainting mask, allowing us to refine the 3DGS for inpainting purposes.Through extensive experiments on benchmark datasets, we confirm that our 3DGIC outperforms current state-of-the-art 3D inpainting methods quantitatively and qualitatively.
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。