SplatFill: 3D Scene Inpainting via Depth-Guided Gaussian Splatting
This addresses the challenge of inpainting occluded or edited areas in 3D scene representations for applications like VR and editing, though it appears incremental as it builds on existing 3DGS methods.
The paper tackled the problem of inpainting missing regions in 3D Gaussian Splatting scenes, achieving state-of-the-art perceptual quality and a 24.5% reduction in training time.
3D Gaussian Splatting (3DGS) has enabled the creation of highly realistic 3D scene representations from sets of multi-view images. However, inpainting missing regions, whether due to occlusion or scene editing, remains a challenging task, often leading to blurry details, artifacts, and inconsistent geometry. In this work, we introduce SplatFill, a novel depth-guided approach for 3DGS scene inpainting that achieves state-of-the-art perceptual quality and improved efficiency. Our method combines two key ideas: (1) joint depth-based and object-based supervision to ensure inpainted Gaussians are accurately placed in 3D space and aligned with surrounding geometry, and (2) we propose a consistency-aware refinement scheme that selectively identifies and corrects inconsistent regions without disrupting the rest of the scene. Evaluations on the SPIn-NeRF dataset demonstrate that SplatFill not only surpasses existing NeRF-based and 3DGS-based inpainting methods in visual fidelity but also reduces training time by 24.5%. Qualitative results show our method delivers sharper details, fewer artifacts, and greater coherence across challenging viewpoints.