AI RESEARCH
FluSplat: Sparse-View 3D Editing without Test-Time Optimization
arXiv CS.CV
•
ArXi:2604.20038v1 Announce Type: new Recent advances in text-guided image editing and 3D Gaussian Splatting (3DGS) have enabled high-quality 3D scene manipulation. However, existing pipelines rely on iterative edit-and-fit optimization at test time, alternating between 2D diffusion editing and 3D reconstruction. This process is computationally expensive, scene-specific, and prone to cross-view inconsistencies. We propose a feed-forward framework for cross-view consistent 3D scene editing from sparse views.