TransSplat：不平衡语义传输用于语言驱动的3DGS编辑
TransSplat: Unbalanced Semantic Transport for Language-Driven 3DGS Editing
AI总结：
TransSplat通过不平衡语义传输解决语言驱动3DGS编辑中2D证据与3D高斯之间的语义对应问题，提升局部编辑精度和结构一致性。
摘要：
语言驱动的3D高斯散射（3DGS）编辑为VR/AR中修改复杂场景提供了更便捷的方法。标准流程通常采用两阶段策略：首先编辑多个2D视图，然后优化3D表示以匹配这些编辑观察。现有方法主要通过多视图特征融合、注意力过滤或迭代重校准来提高视图一致性。然而，它们未能明确解决更根本的问题：编辑2D证据与3D高斯之间的语义对应。为此，我们提出了TransSplat，将语言驱动的3DGS编辑建模为多视图不平衡语义传输问题。具体而言，我们的方法在可见的高斯和视图特定的编辑原型之间建立对应关系，从而显式表征编辑2D证据与3D高斯之间的语义关系。它进一步恢复了一个跨视图共享的标准化3D编辑场，以指导统一的3D外观更新。此外，我们使用传输残差来抑制非目标区域的错误编辑，缓解编辑泄漏并提高局部控制精度。定性与定量结果表明，与现有以提高视图一致性为中心的3D编辑方法相比，TransSplat在局部编辑精度和结构一致性方面表现更优。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
