让3D高斯点直接编辑，解决跨视角不一致问题
Variation-aware Flexible 3D Gaussian Editing
- 直接预测高斯点属性变化，无需2D中间步骤
- 支持多种2D编辑知识迁移，统一建模属性变化
- 提升编辑灵活性与效率，适合3D内容创作人群
3D高斯点云的间接编辑方法近年取得显著进展，这类方法先在渲染的2D空间中进行编辑，再将修改投影回3D空间。然而该范式不可避免引入跨视图不一致性，并限制了编辑的灵活性与效率。为此，我们提出VF-Editor，通过前馈方式直接预测高斯原语的属性变化，实现原生3D编辑。为准确高效地估计这些变化，我们设计了一个从2D编辑知识中蒸馏出的新型变化预测器。该预测器将输入编码生成变化场，并采用两个可学习的并行解码函数，迭代推断每个3D高斯点的属性变化。得益于统一设计，VF-Editor能无缝融合多种2D编辑器与策略的知识，实现单一预测器向3D域的灵活有效知识迁移。在公开与私有数据集上的大量实验揭示了间接编辑管道的固有局限性，并验证了本方法的有效性与灵活性。
原文摘要 · Abstract (English)
Indirect editing methods for 3D Gaussian Splatting (3DGS) have recently witnessed significant advancements. These approaches operate by first applying edits in the rendered 2D space and subsequently projecting the modifications back into 3D. However, this paradigm inevitably introduces cross-view inconsistencies and constrains both the flexibility and efficiency of the editing process. To address these challenges, we present VF-Editor, which enables native editing of Gaussian primitives by predicting attribute variations in a feedforward manner. To accurately and efficiently estimate these variations, we design a novel variation predictor distilled from 2D editing knowledge. The predictor encodes the input to generate a variation field and employs two learnable, parallel decoding functions to iteratively infer attribute changes for each 3D Gaussian. Thanks to its unified design, VF-Editor can seamlessly distill editing knowledge from diverse 2D editors and strategies into a single predictor, allowing for flexible and effective knowledge transfer into the 3D domain. Extensive experiments on both public and private datasets reveal the inherent limitations of indirect editing pipelines and validate the effectiveness and flexibility of our approach.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。