解决3D编辑的不一致与结构扭曲问题，实现高效精准修改。
Towards Scalable and Consistent 3D Editing
- 用双引导注意力和时序自适应门控，分离可编辑区域与保留结构。
- 在11.6万组数据上训练，测试集达1500对，显著提升一致性与保真度。
- 无需人工3D掩码，适合游戏、影视等沉浸式内容快速迭代场景。
3D编辑——即对3D资产的几何或外观进行局部修改——在沉浸式内容创作、数字娱乐和AR/VR中应用广泛。然而，与2D编辑相比，其仍面临跨视角一致性、结构保真度和细粒度控制等挑战。现有方法常速度慢、易产生几何失真，或依赖人工制作且易错的3D掩码。为此，本文从数据与模型两方面推进：数据上，构建了当前最大的成对3D编辑基准3DEditVerse，包含116,309个高质量训练对和1,500个精心筛选的测试对；该数据通过姿态驱动的几何编辑与基础模型引导的外观编辑互补生成，保障编辑局部性、多视图一致性与语义对齐。模型上，提出3DEditFormer，一种保持3D结构的条件变换器，通过增强图像到3D生成的双引导注意力与时间自适应门控，解耦可编辑区域与保留结构，实现无需辅助3D掩码的精确一致编辑。大量实验证明，本框架在定量与定性指标上均优于现有最优基线，建立实用且可扩展的3D编辑新标准。数据与代码将公开。项目页面：https://www.lv-lab.org/3DEditFormer/
原文摘要 · Abstract (English)
3D editing - the task of locally modifying the geometry or appearance of a 3D asset - has wide applications in immersive content creation, digital entertainment, and AR/VR. However, unlike 2D editing, it remains challenging due to the need for cross-view consistency, structural fidelity, and fine-grained controllability. Existing approaches are often slow, prone to geometric distortions, or dependent on manual and accurate 3D masks that are error-prone and impractical. To address these challenges, we advance both the data and model fronts. On the data side, we introduce 3DEditVerse, the largest paired 3D editing benchmark to date, comprising 116,309 high-quality training pairs and 1,500 curated test pairs. Built through complementary pipelines of pose-driven geometric edits and foundation model-guided appearance edits, 3DEditVerse ensures edit locality, multi-view consistency, and semantic alignment. On the model side, we propose 3DEditFormer, a 3D-structure-preserving conditional transformer. By enhancing image-to-3D generation with dual-guidance attention and time-adaptive gating, 3DEditFormer disentangles editable regions from preserved structure, enabling precise and consistent edits without requiring auxiliary 3D masks. Extensive experiments demonstrate that our framework outperforms state-of-the-art baselines both quantitatively and qualitatively, establishing a new standard for practical and scalable 3D editing. Dataset and code will be released. Project: https://www.lv-lab.org/3DEditFormer/
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。