在3D高斯潑濺中實現穩健的3D遮罩部分層級編輯，結合正則化分數蒸餾採樣

Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling

July 15, 2025

作者: Hayeon Kim, Ji Ha Jang, Se Young Chun

cs.AI

摘要

近期在3D神經表示和實例級編輯模型方面的進展，使得高效創建高質量3D內容成為可能。然而，實現精確的局部3D編輯仍然具有挑戰性，特別是對於高斯潑濺技術而言，這是由於多視角2D部件分割的不一致性以及分數蒸餾採樣（SDS）損失固有的模糊性所致。為解決這些限制，我們提出了RoMaP，一種新穎的局部3D高斯編輯框架，能夠實現精確且大幅度的部件級修改。首先，我們引入了一個基於3D幾何感知標籤預測（3D-GALP）的魯棒3D掩碼生成模塊，該模塊利用球諧函數（SH）係數來建模視角依賴的標籤變化和軟標籤屬性，從而生成跨視角準確且一致的部件分割。其次，我們提出了一種正則化的SDS損失，它將標準SDS損失與額外的正則化項相結合。特別是，通過我們的計劃潛在混合與部件（SLaMP）編輯方法引入了L1錨定損失，該方法生成高質量的部件編輯2D圖像，並將修改限制在目標區域內，同時保持上下文一致性。額外的正則化項，如高斯先驗移除，通過允許超出現有上下文的變化進一步提高了靈活性，而魯棒的3D掩碼則防止了意外編輯。實驗結果表明，我們的RoMaP在重建和生成的高斯場景及物體上，無論是定性還是定量，都實現了最先進的局部3D編輯，使得更為魯棒和靈活的部件級3D高斯編輯成為可能。代碼可在https://janeyeon.github.io/romap獲取。

English

Recent advances in 3D neural representations and instance-level editing models have enabled the efficient creation of high-quality 3D content. However, achieving precise local 3D edits remains challenging, especially for Gaussian Splatting, due to inconsistent multi-view 2D part segmentations and inherently ambiguous nature of Score Distillation Sampling (SDS) loss. To address these limitations, we propose RoMaP, a novel local 3D Gaussian editing framework that enables precise and drastic part-level modifications. First, we introduce a robust 3D mask generation module with our 3D-Geometry Aware Label Prediction (3D-GALP), which uses spherical harmonics (SH) coefficients to model view-dependent label variations and soft-label property, yielding accurate and consistent part segmentations across viewpoints. Second, we propose a regularized SDS loss that combines the standard SDS loss with additional regularizers. In particular, an L1 anchor loss is introduced via our Scheduled Latent Mixing and Part (SLaMP) editing method, which generates high-quality part-edited 2D images and confines modifications only to the target region while preserving contextual coherence. Additional regularizers, such as Gaussian prior removal, further improve flexibility by allowing changes beyond the existing context, and robust 3D masking prevents unintended edits. Experimental results demonstrate that our RoMaP achieves state-of-the-art local 3D editing on both reconstructed and generated Gaussian scenes and objects qualitatively and quantitatively, making it possible for more robust and flexible part-level 3D Gaussian editing. Code is available at https://janeyeon.github.io/romap.