用扩散模型无训练修复3D高斯点云的稀疏视图重建缺陷
FixingGS: Enhancing 3D Gaussian Splatting via Training-Free Score Distillation
- 利用现有扩散模型蒸馏更准确的先验，提升多视角一致性
- 在稀疏视图下实现更清晰的结构与更合理的细节填充
- 无需训练，适合快速增强3D重建质量的场景
近期，3D高斯点云（3DGS）在三维重建与新视角合成中表现卓越。然而，从稀疏视角重建3D场景仍面临视觉信息不足的问题，导致3D表示中持续存在明显伪影。为解决此问题，现有方法引入生成先验以消除伪影并补全缺失内容，但难以保证多视角一致性，常导致结构模糊与不合理细节。本文提出FixingGS，一种无训练方法，充分利用现有扩散模型能力，通过新颖的蒸馏策略生成更精确且跨视角一致的扩散先验，有效去除伪影并完成图像修复。此外，我们设计自适应渐进增强方案，进一步优化欠约束区域的重建效果。大量实验表明，FixingGS超越现有最先进方法，在视觉质量和重建性能上均取得显著提升。代码将公开。
原文摘要 · Abstract (English)
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.
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。