AI RESEARCH
TransSplat: Unbalanced Semantic Transport for Language-Driven 3DGS Editing
arXiv CS.CV
•
ArXi:2604.19571v1 Announce Type: new Language-driven 3D Gaussian Splatting (3DGS) editing provides a 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 fundamental issue: the semantic correspondence between edited 2D evidence and 3D Gaussians.