多对象3D高斯泼溅场景的单步修复方法基准测试
Benchmarking Single-Step Inpainting Methods for Multi-Object 3D Gaussian Splatting Scenes
AI总结：
针对3D高斯泼溅场景中的对象移除与修复任务，比较了2D修复器在3D一致性上的表现，发现基于重建的修复器优于生成扩散模型，且从头初始化场景比微调现有场景效果更好，同时引入了一个带真实数据的新多对象场景。
摘要：
对象移除和修复3D高斯泼溅（3DGS）场景面临跨相机视图的3D一致性等挑战。在比较2D修复器及其对3D领域的适用性时，我们发现基于重建的修复器在3D一致性上优于生成扩散模型。将这些2D修复器集成到创建和微调3DGS场景的不同单步方法中，我们的结果表明，从头初始化场景比微调现有场景产生更高质量的结果。使用最先进的生成式2D修复器，我们创建了一个简单的基线，以强调在3D设置中先移除对象再进行修复的重要性。由于360°数据集很少包含真实世界的地面真值，且具有挑战性的遮挡场景同样稀少，我们引入了一个新的多对象场景，其中包含记录的地面真值数据和多个存在对象遮挡的视图。
英文摘要：
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.
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。
