对比2D修复方法在3D高斯点云中的表现，发现重建类模型更保真。
Benchmarking Single-Step Inpainting Methods for Multi-Object 3D Gaussian Splatting Scenes
- 用2D重建式修复器提升3DGS场景的视图一致性
- 从零初始化生成的3D场景质量优于微调现有场景
- 提出含真实遮挡数据的新多物体360°测试集
3D高斯点云（3DGS）场景中的物体移除与修复面临跨视角3D一致性挑战。对比2D修复模型与生成式扩散模型在3D场景中的适用性，结果表明基于重建的2D修复器在3D一致性方面表现更优。将这些2D修复器集成到不同单步方法中用于创建和微调3DGS场景，发现从零初始化场景比微调已有场景获得更高质量结果。使用当前最先进的生成式2D修复器，构建了一个简洁基线，强调在3D设置中需先移除物体再修复的重要性。由于360°数据集极少包含真实地面实况，且复杂遮挡场景稀缺，本文引入一个新型多物体场景，具备真实标注数据和多视角遮挡情况。
原文摘要 · Abstract (English)
The tasks of object removal and inpainting 3D Gaussian Splatting (3DGS) scenes face challenges such as 3D consistency across camera views. In comparing 2D inpainters and their suitability for the 3D domain, we find that reconstruction-based inpainters outperform generative diffusion models in 3D consistency. Integrating these 2D inpainters into different single-step methods for creating and finetuning 3DGS scenes, our results indicate that initializing the scene from scratch produces higher quality results than finetuning the existing scene. Using a state-of-the-art generative 2D inpainter, we create a straightforward baseline to underline the importance of object removal before inpainting in the 3D setting. Since 360° datasets rarely include real-world ground truths, and challenging occlusion scenarios are equally sparse, we introduce a novel multi-object scene with recorded ground truth data and many views with object occlusions.
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。