FixingGS: Enhancing 3D Gaussian Splatting via Training-Free Score Distillation
This work addresses the challenge of sparse-view 3D reconstruction for applications like novel view synthesis, though it appears incremental as it builds on existing diffusion-based priors.
The paper tackles the problem of artifacts and missing content in 3D Gaussian Splatting reconstructions from sparse viewpoints by proposing FixingGS, a training-free method that uses diffusion priors to enhance multi-view consistency and visual quality, achieving superior performance over state-of-the-art methods.
Recently, 3D Gaussian Splatting (3DGS) has demonstrated remarkable success in 3D reconstruction and novel view synthesis. However, reconstructing 3D scenes from sparse viewpoints remains highly challenging due to insufficient visual information, which results in noticeable artifacts persisting across the 3D representation. To address this limitation, recent methods have resorted to generative priors to remove artifacts and complete missing content in under-constrained areas. Despite their effectiveness, these approaches struggle to ensure multi-view consistency, resulting in blurred structures and implausible details. In this work, we propose FixingGS, a training-free method that fully exploits the capabilities of the existing diffusion model for sparse-view 3DGS reconstruction enhancement. At the core of FixingGS is our distillation approach, which delivers more accurate and cross-view coherent diffusion priors, thereby enabling effective artifact removal and inpainting. In addition, we propose an adaptive progressive enhancement scheme that further refines reconstructions in under-constrained regions. Extensive experiments demonstrate that FixingGS surpasses existing state-of-the-art methods with superior visual quality and reconstruction performance. Our code will be released publicly.