AI 中文总结
FocusGS将局部修复与确定性编辑统一为复合空间增量，解决3D高斯资产的局部维护问题，提升目标区域PSNR，优于文本驱动基线，提供轻量可验证的3DGS维护算子。
AI 中文摘要
3D高斯溅射（3DGS）正从一次性重建发展为可交付、可检查和可维护的视觉资产。现有工作流程聚焦于全局重建、训练时密度控制或开放式生成编辑，导致训练后的资产缺乏精确的局部维护。我们提出FocusGS，将局部修复与确定性编辑统一为复合空间增量。修复是纯加法特例：其基础操作项为空，仅添加局部高斯基；确定性编辑采用擦除-插入分解（EIF），结合旧载体擦除与新内容插入。FocusGS解决空间梯度匮乏问题：局部修复在93个评估视图上使目标区域PSNR提升7.91 dB；在全部83次确定性编辑试验中，目标感兴趣区域（ROI）均有改善，试验平均编辑ROI PSNR为21.97 dB，平均增益达+11.05 dB；在5个公开编辑案例中，FocusGS-EIF达到33.17 dB目标掩码PSNR和0.994目标增量相关性，而两个文本驱动基线均无法完成指定更新。FocusGS提供轻量、可验证的3DGS维护算子。
英文摘要
3D Gaussian Splatting (3DGS) is evolving from one-time reconstruction into deliverable, inspectable, and maintainable visual assets. Existing workflows focus on global reconstruction, training-time density control, or open-ended generative editing, leaving trained assets without precise local maintenance. We propose FocusGS, which unifies local repair and deterministic editing as composite spatial deltas. Repair is the purely additive special case: its base-manipulation term is empty, and it adds only local Gaussian bases; deterministic editing uses erase-insert factorization (EIF) to combine old-carrier erasure with new-content insertion. FocusGS addresses spatial gradient starvation: local repair raises target-region PSNR by 7.91 dB over 93 evaluation views. Across all 83 deterministic editing trials, the target ROI improves, with a trial-averaged mean edited ROI PSNR of 21.97 dB and a mean gain of +11.05 dB; across five public editing cases, FocusGS-EIF reaches 33.17 dB Target-mask PSNR and 0.994 Target-delta Correlation, while both text-driven baselines fail to complete the prescribed updates. FocusGS provides a lightweight, verifiable 3DGS maintenance operator.
Comments8 pages, 6 figures, 5 tables. Ancillary demonstration video included
