FluSplat: Sparse-View 3D Editing without Test-Time Optimization

arXiv:2604.20038v1 Announce Type: new Abstract: 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. Instead of enforcing consistency through iterative 3D refinement, we introduce a cross-view regularization scheme in the image domain during training. By jointly supervising multi-view edits with geometric alignment constraints, our model produces view-consistent results without per-scene optimization at inference. The edited views are then lifted into 3D via a feedforward 3DGS model, yielding a coherent 3DGS representation in a single forward pass. Experiments demonstrate competitive editing fidelity and substantially improved cross-view consistency compared to optimization-based methods, while reducing inference time by orders of magnitude.

Related

• NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation
• Hybrid Latents -- Geometry-Appearance-Aware Surfel Splatting
• The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images with Minimal 3D Knowledge
• Scene-Agnostic Object-Centric Representation Learning for 3D Gaussian Splatting

Source: arXiv cs.CV | 2026-04-23