用2D编辑实时更新3D高斯点云，交互流畅且保持细节。
SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training
- 基于测试时训练的前馈模型，直接预测高斯属性更新。
- 支持局部细节修复、涂改与全局变色，交互速度下完成。
- 适合需要快速迭代的3D内容创作者，如动画师或建模师。
3D高斯点云的兴起彻底改变了逼真3D资产的创建方式，但其交互式精修与编辑仍存在关键空白。现有基于扩散或优化的方法难以胜任，因速度慢、破坏原始特征或缺乏精细控制。为此，我们提出SplatPainter，一种状态感知的前馈模型，可从用户提供的2D视图中持续编辑3D高斯资产。该方法直接预测紧凑、特征丰富的高斯表示的属性更新，并利用测试时训练实现状态感知的迭代流程。其多功能性使单一架构能完成高保真局部细节修复、局部涂改和一致全局重着色，均在交互速度下实现，为流畅直观的3D内容创作铺平道路。
原文摘要 · Abstract (English)
The rise of 3D Gaussian Splatting has revolutionized photorealistic 3D asset creation, yet a critical gap remains for their interactive refinement and editing. Existing approaches based on diffusion or optimization are ill-suited for this task, as they are often prohibitively slow, destructive to the original asset's identity, or lack the precision for fine-grained control. To address this, we introduce SplatPainter, a state-aware feedforward model that enables continuous editing of 3D Gaussian assets from user-provided 2D view(s). Our method directly predicts updates to the attributes of a compact, feature-rich Gaussian representation and leverages Test-Time Training to create a state-aware, iterative workflow. The versatility of our approach allows a single architecture to perform diverse tasks, including high-fidelity local detail refinement, local paint-over, and consistent global recoloring, all at interactive speeds, paving the way for fluid and intuitive 3D content authoring.
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。