通过分离高斯位置自由度，改善稀疏视角3DGS的几何失真问题。
Improving Geometry in Sparse-View 3DGS via Reprojection-based DoF Separation
- 按投影不确定性分离高斯的位置自由度
- 约束不同自由度后几何误差降低，重建更真实
- 适合关注3D重建质量与结构保真的研究者
基于学习的多视角立体视觉模型在稀疏视角三维重建中已达到顶尖水平。然而，直接将3D高斯点阵（3DGS）作为后续优化步骤时面临挑战。我们假设高斯分布中过多的位置自由度（DoFs）会导致几何畸变，以牺牲结构保真度为代价拟合颜色模式。为此，我们提出基于重投影的自由度分离方法，将位置自由度按不确定性区分为平行于图像平面的自由度和沿射线方向的自由度。为独立管理每种自由度，引入重投影过程及针对每类自由度的定制化约束。在多个数据集上的实验表明，分离高斯的位置自由度并施加针对性约束能有效抑制几何伪影，生成视觉与几何上均合理的重建结果。
原文摘要 · Abstract (English)
Recent learning-based Multi-View Stereo models have demonstrated state-of-the-art performance in sparse-view 3D reconstruction. However, directly applying 3D Gaussian Splatting (3DGS) as a refinement step following these models presents challenges. We hypothesize that the excessive positional degrees of freedom (DoFs) in Gaussians induce geometry distortion, fitting color patterns at the cost of structural fidelity. To address this, we propose reprojection-based DoF separation, a method distinguishing positional DoFs in terms of uncertainty: image-plane-parallel DoFs and ray-aligned DoF. To independently manage each DoF, we introduce a reprojection process along with tailored constraints for each DoF. Through experiments across various datasets, we confirm that separating the positional DoFs of Gaussians and applying targeted constraints effectively suppresses geometric artifacts, producing reconstruction results that are both visually and geometrically plausible.
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。