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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Haitao, Chng, Shin-Fang, Zhan, Huangying, Yan, Qingan, Xu, Yi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917427407749120
author Huang, Haitao
Chng, Shin-Fang
Zhan, Huangying
Yan, Qingan
Xu, Yi
author_facet Huang, Haitao
Chng, Shin-Fang
Zhan, Huangying
Yan, Qingan
Xu, Yi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20038
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FluSplat: Sparse-View 3D Editing without Test-Time Optimization
Huang, Haitao
Chng, Shin-Fang
Zhan, Huangying
Yan, Qingan
Xu, Yi
Computer Vision and Pattern Recognition
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.
title FluSplat: Sparse-View 3D Editing without Test-Time Optimization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.20038