TransSplat: Unbalanced Semantic Transport for Language-Driven 3DGS Editing

arXiv:2604.19571v1 Announce Type: new Abstract: Language-driven 3D Gaussian Splatting (3DGS) editing provides a more convenient approach for modifying complex scenes in VR/AR. Standard pipelines typically adopt a two-stage strategy: first editing multiple 2D views, and then optimizing the 3D representation to match these edited observations. Existing methods mainly improve view consistency through multi-view feature fusion, attention filtering, or iterative recalibration. However, they fail to explicitly address a more fundamental issue: the semantic correspondence between edited 2D evidence and 3D Gaussians. To tackle this problem, we propose TransSplat, which formulates language-driven 3DGS editing as a multi-view unbalanced semantic transport problem. Specifically, our method establishes correspondences between visible Gaussians and view-specific editing prototypes, thereby explicitly characterizing the semantic relationship between edited 2D evidence and 3D Gaussians. It further recovers a cross-view shared canonical 3D edit field to guide unified 3D appearance updates. In addition, we use transport residuals to suppress erroneous edits in non-target regions, mitigating edit leakage and improving local control precision. Qualitative and quantitative results show that, compared with existing 3D editing methods centered on enhancing view consistency, TransSplat achieves superior performance in local editing accuracy and structural consistency.

Related

• MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes
• Physically Plausible Human-Object Rendering from Sparse Views via 3D Gaussian Splatting
• GaussianFlow SLAM: Monocular Gaussian Splatting SLAM Guided by GaussianFlow
• ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-based 3D Scene Understanding
• PartNerFace: Part-based Neural Radiance Fields for Animatable Facial Avatar Reconstruction

Source: arXiv cs.CV | 2026-04-22