Signed distance-radiance field (SDF-NeRF) is a promising environment representation that offers both photo-realistic rendering and geometric reasoning such as proximity queries for collision avoidance. However, the slow training speed and convergence of SDF-NeRF hinder their use in practical robotic systems. We propose SplatSDF, a novel SDF-NeRF architecture that accelerates convergence using 3D Gaussian splats (3DGS), which can be quickly pre-trained. Unlike prior approaches that introduce a consistency loss between separate 3DGS and SDF-NeRF models, SplatSDF directly fuses 3DGS at an architectural level by consuming it as an input to SDF-NeRF during training. This is achieved using a novel sparse 3DGS fusion strategy that injects neural embeddings of 3DGS into SDF-NeRF around the object surface, while also permitting inference without 3DGS for minimal operation. Experimental results show SplatSDF achieves 3X faster convergence to the same geometric accuracy than the best baseline, and outperforms state-of-the-art SDF-NeRF methods in terms of chamfer distance and peak signal to noise ratio, unlike consistency loss-based approaches that in fact provide limited gains. We also present computational techniques for accelerating gradient and Hessian steps by 3X. We expect these improvements will contribute to deploying SDF-NeRF on practical systems.

翻译：符号距离-辐射场（SDF-NeRF）是一种前景广阔的环境表示方法，既能实现照片级真实感渲染，又能支持几何推理（如用于避障的邻近查询）。然而，SDF-NeRF缓慢的训练速度与收敛过程阻碍了其在实用机器人系统中的部署。我们提出SplatSDF，一种新颖的SDF-NeRF架构，通过利用可快速预训练的3D高斯溅射（3DGS）来加速收敛。与先前在独立3DGS和SDF-NeRF模型间引入一致性损失的方法不同，SplatSDF在架构层面直接融合3DGS，将其作为训练期间SDF-NeRF的输入进行消费。这是通过一种新颖的稀疏3DGS融合策略实现的，该策略将3DGS的神经嵌入注入到物体表面周围的SDF-NeRF中，同时允许在无需3DGS的情况下进行推理以实现最小化运行。实验结果表明，SplatSDF达到相同几何精度的收敛速度比最佳基线快3倍，并且在倒角距离和峰值信噪比方面优于最先进的SDF-NeRF方法，这与基于一致性损失的方法（实际上增益有限）形成鲜明对比。我们还提出了将梯度和Hessian计算步骤加速3倍的数值计算技术。我们期望这些改进将有助于在实际系统中部署SDF-NeRF。