Scene completion refers to obtaining dense scene representation from an incomplete perception of complex 3D scenes. This helps robots detect multi-scale obstacles and analyse object occlusions in scenarios such as autonomous driving. Recent advances show that implicit representation learning can be leveraged for continuous scene completion and achieved through physical constraints like Eikonal equations. However, former Eikonal completion methods only demonstrate results on watertight meshes at a scale of tens of meshes. None of them are successfully done for non-watertight LiDAR point clouds of open large scenes at a scale of thousands of scenes. In this paper, we propose a novel Eikonal formulation that conditions the implicit representation on localized shape priors which function as dense boundary value constraints, and demonstrate it works on SemanticKITTI and SemanticPOSS. It can also be extended to semantic Eikonal scene completion with only small modifications to the network architecture. With extensive quantitative and qualitative results, we demonstrate the benefits and drawbacks of existing Eikonal methods, which naturally leads to the new locally conditioned formulation. Notably, we improve IoU from 31.7% to 51.2% on SemanticKITTI and from 40.5% to 48.7% on SemanticPOSS. We extensively ablate our methods and demonstrate that the proposed formulation is robust to a wide spectrum of implementation hyper-parameters. Codes and models are publicly available at https://github.com/AIR-DISCOVER/LODE.

翻译：场景补全旨在从不完整的复杂三维场景感知中获取稠密化场景表示，这有助于自动驾驶等场景中机器人检测多尺度障碍物并分析物体遮挡。近期研究表明，隐式表示学习可结合Eikonal方程等物理约束实现连续场景补全。然而，现有基于Eikonal的补全方法仅在数十个水密网格规模上验证有效性，尚未成功应用于数千个大规模开放场景的非水密LiDAR点云。本文提出一种新型Eikonal公式，通过将隐式表示约束于局部形状先验（作为稠密边界值约束），并在SemanticKITTI和SemanticPOSS数据集上验证其可行性。该方法仅需对网络架构进行微小修改即可扩展至语义级Eikonal场景补全。通过大量定量与定性实验，我们揭示了现有Eikonal方法的优劣，并自然推导出新的局部约束公式。值得注意的是，在SemanticKITTI数据集上IoU从31.7%提升至51.2%，在SemanticPOSS数据集上从40.5%提升至48.7%。我们通过充分消融实验证明，所提公式对广泛的超参数设置具有鲁棒性。代码与模型已开源：https://github.com/AIR-DISCOVER/LODE。