SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training
This addresses the need for fluid and intuitive 3D content authoring for creators, though it is incremental as it builds on 3D Gaussian Splatting.
The paper tackles the problem of interactive refinement and editing of 3D Gaussian assets, which are slow or imprecise with existing methods, by introducing SplatPainter, a state-aware feedforward model that enables continuous editing from 2D views at interactive speeds, achieving high-fidelity local detail refinement, paint-over, and global recoloring.
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 \ourmethod, 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.