用深度引导的高斯点云修复3D场景缺失区域，效果更清晰、更快。
SplatFill: 3D Scene Inpainting via Depth-Guided Gaussian Splatting
- 结合深度与物体监督，精准定位修复区域的高斯点。
- 修复后细节更锐利，错误区域减少24.5%训练时间。
- 适合需要高质量3D场景编辑的视觉生成研究者。
3D高斯溅射（3DGS）已实现从多视角图像构建高度逼真的3D场景表示。然而，由于遮挡或场景编辑导致的缺失区域修复仍具挑战性，常引发模糊细节、伪影和几何不一致问题。本文提出SplatFill，一种新颖的深度引导式3DGS场景修复方法，在感知质量上达到当前最佳水平，并提升效率。该方法融合两个关键思想：(1) 联合深度监督与物体监督，确保修复的高斯点在3D空间中准确放置并与周围几何对齐；(2) 提出一致性感知优化策略，可选择性识别并修正不一致区域，而不破坏场景其他部分。在SPIn-NeRF数据集上的评估表明，SplatFill不仅在视觉保真度上超越现有基于NeRF和3DGS的修复方法，还减少了24.5%的训练时间。定性结果展示其在复杂视角下具有更锐利的细节、更少的伪影和更高的整体一致性。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has enabled the creation of highly realistic 3D scene representations from sets of multi-view images. However, inpainting missing regions, whether due to occlusion or scene editing, remains a challenging task, often leading to blurry details, artifacts, and inconsistent geometry. In this work, we introduce SplatFill, a novel depth-guided approach for 3DGS scene inpainting that achieves state-of-the-art perceptual quality and improved efficiency. Our method combines two key ideas: (1) joint depth-based and object-based supervision to ensure inpainted Gaussians are accurately placed in 3D space and aligned with surrounding geometry, and (2) we propose a consistency-aware refinement scheme that selectively identifies and corrects inconsistent regions without disrupting the rest of the scene. Evaluations on the SPIn-NeRF dataset demonstrate that SplatFill not only surpasses existing NeRF-based and 3DGS-based inpainting methods in visual fidelity but also reduces training time by 24.5%. Qualitative results show our method delivers sharper details, fewer artifacts, and greater coherence across challenging viewpoints.
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。