AI RESEARCH
Benchmarking Single-Step Inpainting Methods for Multi-Object 3D Gaussian Splatting Scenes
arXiv CS.CV
•
ArXi:2605.30987v1 Announce Type: new 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.