基于自约束先验的 3D 高斯泼溅高保真表面重建
3D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstruction
提出一种自约束先验（由渲染深度融合的 TSDF 网格）来约束 3D 高斯运动，通过带状区域和渐进收窄策略提升表面重建精度，可直接用于改进 3DGS 的几何质量。
原文依据 we propose a self-constrained prior to constraining the movement of 3D Gaussians, aiming for more accurate depth rendering
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论通过 3DGS 或神经辐射场对辐射场建模，3D 表面渲染已被彻底革新。尽管 3DGS 在渲染质量或速度上优于神经辐射场，但通过 3DGS 恢复高保真表面仍有改进空间。为解决该问题，我们提出一种自约束先验来约束 3D 高斯的运动，旨在获得更准确的深度渲染。我们的自约束先验是一个在 3D 高斯学习过程中由渲染深度融合而成的 TSDF 网格。该先验在估计表面两侧度量一个带状区域，以对正确的 3D 高斯施加更具体的约束，例如移除带状区域外的 3D 高斯，鼓励靠近带状区域中心的高斯具有更大的不透明度，或靠近带状区域边界的高斯具有更小的不透明度。我们通过融合通常更准确的近期深度图像来定期更新先验，并逐步收窄带状区域以收紧对高斯运动的约束。我们在广泛使用的基准上的评估证明了我们的想法，并报告了优于最优方法的结果。
英文原文摘要 1155 字符
Rendering 3D surfaces has been revolutionized within the modeling of radiance fields through either 3DGS or NeRF. Although 3DGS has shown advantages over NeRF in terms of rendering quality or speed, there is still room for improvement in recovering high fidelity surfaces through 3DGS. To resolve this issue, we propose a self-constrained prior to constraining the movement of 3D Gaussians, aiming for more accurate depth rendering. Our self-constrained prior is a TSDF grid fused by the rendered depth during the learning of 3D Gaussians. The prior measures a band on both sides of the estimated surface for imposing more specific constraints on the right 3D Gaussians, such as removing 3D Gaussians outside the band, encouraging larger opacity for Gaussians near the center of the band or smaller opacity for Gaussians near the boundary of the band. We regularly update the prior by fusing more recent depth images which are usually more accurate, and progressively narrow the band to tighten the constraint on Gaussian movements. We justify our idea and report our superiority over the state-of-the-art methods in evaluations on widely used benchmarks.