通过语义与深度约束，提升稀疏视角下3D高斯点云的渲染质量。
See In Detail: Enhancing Sparse-view 3D Gaussian Splatting with Local Depth and Semantic Regularization
- 引入预训练DINO-ViT特征进行多视角语义一致性正则化。
- 在LLFF数据集上提升0.4dB PSNR，减少畸变并增强细节。
- 适合需要高质量稀疏视图合成的场景，如三维重建与VR应用。
3D高斯点云（3DGS）在新视角合成中表现优异，但在输入视角稀疏时渲染质量下降，导致内容失真、细节缺失，限制了实际应用。针对这一问题，我们提出一种稀疏视角3DGS方法。鉴于稀疏视图重建本质上是病态问题，引入先验信息至关重要。我们提出基于预训练DINO-ViT模型特征的语义正则化，以保证多视角语义一致性；同时引入局部深度正则化，约束深度值以提升对未见视角的泛化能力。所提方法优于现有先进方法，在LLFF数据集上实现最高0.4dB的PSNR提升，显著降低畸变并改善视觉质量。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has shown remarkable performance in novel view synthesis. However, its rendering quality deteriorates with sparse inphut views, leading to distorted content and reduced details. This limitation hinders its practical application. To address this issue, we propose a sparse-view 3DGS method. Given the inherently ill-posed nature of sparse-view rendering, incorporating prior information is crucial. We propose a semantic regularization technique, using features extracted from the pretrained DINO-ViT model, to ensure multi-view semantic consistency. Additionally, we propose local depth regularization, which constrains depth values to improve generalization on unseen views. Our method outperforms state-of-the-art novel view synthesis approaches, achieving up to 0.4dB improvement in terms of PSNR on the LLFF dataset, with reduced distortion and enhanced visual quality.
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。