A signed distance function (SDF) is a useful representation for continuous-space geometry and many related operations, including rendering, collision checking, and mesh generation. Hence, reconstructing SDF from image observations accurately and efficiently is a fundamental problem. Recently, neural implicit SDF (SDF-NeRF) techniques, trained using volumetric rendering, have gained a lot of attention. Compared to earlier truncated SDF (TSDF) fusion algorithms that rely on depth maps and voxelize continuous space, SDF-NeRF enables continuous-space SDF reconstruction with better geometric and photometric accuracy. However, the accuracy and convergence speed of scene-level SDF reconstruction require further improvements for many applications. With the advent of 3D Gaussian Splatting (3DGS) as an explicit representation with excellent rendering quality and speed, several works have focused on improving SDF-NeRF by introducing consistency losses on depth and surface normals between 3DGS and SDF-NeRF. However, loss-level connections alone lead to incremental improvements. We propose a novel neural implicit SDF called "SplatSDF" to fuse 3DGSandSDF-NeRF at an architecture level with significant boosts to geometric and photometric accuracy and convergence speed. Our SplatSDF relies on 3DGS as input only during training, and keeps the same complexity and efficiency as the original SDF-NeRF during inference. Our method outperforms state-of-the-art SDF-NeRF models on geometric and photometric evaluation by the time of submission.
有符号距离函数（Signed Distance Function, SDF）是一种有效的连续空间几何表示方式，广泛应用于渲染、碰撞检测和网格生成等相关操作。因此，如何从图像观测中准确且高效地重建 SDF 是一个基础性问题。最近，基于体渲染训练的神经隐式 SDF 技术（SDF-NeRF）引起了广泛关注。相比于依赖深度图并将连续空间体素化的早期截断 SDF（TSDF）融合算法，SDF-NeRF 实现了更高几何和光度精度的连续空间 SDF 重建。然而，在场景级 SDF 重建的精度和收敛速度方面，仍有许多应用需要进一步改进。 随着 3D 高斯投影（3D Gaussian Splatting, 3DGS）作为一种具有出色渲染质量和速度的显式表示的出现，一些研究致力于通过在深度和表面法线之间引入一致性损失来改进 SDF-NeRF。然而，单纯基于损失级别的连接只能带来渐进式的改进。我们提出了一种新颖的神经隐式 SDF 方法，称为“SplatSDF”，在架构层面融合了 3DGS 和 SDF-NeRF，显著提升了几何和光度精度以及收敛速度。SplatSDF 在训练过程中仅依赖 3DGS 输入，而在推理时保持与原始 SDF-NeRF 相同的复杂度和效率。我们的方法在几何和光度评估方面优于截至投稿时的最先进 SDF-NeRF 模型。