Implicit neural representations have shown compelling results in offline 3D reconstruction and also recently demonstrated the potential for online SLAM systems. However, applying them to autonomous 3D reconstruction, where a robot is required to explore a scene and plan a view path for the reconstruction, has not been studied. In this paper, we explore for the first time the possibility of using implicit neural representations for autonomous 3D scene reconstruction by addressing two key challenges: 1) seeking a criterion to measure the quality of the candidate viewpoints for the view planning based on the new representations, and 2) learning the criterion from data that can generalize to different scenes instead of a hand-crafting one. To solve the challenges, firstly, a proxy of Peak Signal-to-Noise Ratio (PSNR) is proposed to quantify a viewpoint quality; secondly, the proxy is optimized jointly with the parameters of an implicit neural network for the scene. With the proposed view quality criterion from neural networks (termed as Neural Uncertainty), we can then apply implicit representations to autonomous 3D reconstruction. Our method demonstrates significant improvements on various metrics for the rendered image quality and the geometry quality of the reconstructed 3D models when compared with variants using TSDF or reconstruction without view planning. Project webpage https://kingteeloki-ran.github.io/NeurAR/

翻译：隐式神经表示在离线3D重建中展现了显著成果，近年来也显示出用于在线SLAM系统的潜力。然而，将其应用于自主3D重建——即机器人需探索场景并规划视角路径以实现重建——尚未被研究。本文首次探索了利用隐式神经表示进行自主3D场景重建的可能性，并解决了两个关键挑战：1）基于新型表示，寻求一种准则以衡量候选视角的质量，用于视角规划；2）从数据中学习一种可跨场景泛化的准则，而非手工设计。为解决这些挑战，首先提出了一种峰值信噪比（PSNR）的代理度量来量化视角质量；其次，将该代理度量与场景隐式神经网络的参数联合优化。利用所提出的基于神经网络的视角质量准则（称为神经不确定性），我们可将隐式表示应用于自主3D重建。与使用TSDF或无视角规划重建的变体相比，本方法在渲染图像质量和重建3D模型几何质量的各项指标上均取得了显著提升。项目网页：https://kingteeloki-ran.github.io/NeurAR/