发表机构
University of Waterloo; Karlsruhe Institute of Technology（滑铁卢大学; 卡尔斯鲁厄理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ZVeC提出零样本实例驱动框架，通过分解场景并利用深度和3D高斯条件扩散模型独立补全车辆，再重组场景，在稀疏输入下实现几何一致的点云补全，优于场景级基线。
AI 中文摘要
地下环境中采集的LiDAR点云因遮挡和有限的传感器视角而表现出严重的几何不完整性，这使得在没有大型监督数据集的情况下可靠地进行点云补全变得具有挑战性。我们提出了ZVeC，一个零样本、实例驱动的框架，将场景级补全重新表述为组合式对象级重建。通过将场景分解为语义对象实例，ZVeC减少了杂乱环境中的重建歧义，同时消除了对特定场景训练的需求。每个分割出的车辆使用一个深度和3D高斯条件扩散模型独立完成补全，该模型利用广义几何先验，之后将重建的实例重新组合到原始场景中。为了评估我们的方法，我们构建了一个真实世界的地下停车场密集LiDAR基准。实验结果表明，在定量指标和视觉质量方面，相对于代表性的场景级基线方法，我们的方法持续改进。补全后的点云与测量输入有显著差异（平均KL散度约2.1），但将输入减少到原始LiDAR测量的仅1%时，补全重建的变化很小（KL散度<0.50）。这表明ZVeC即使在极端输入稀疏性下也能产生几何一致的补全结果。
英文摘要
LiDAR point clouds acquired in underground environments exhibit severe geometric incompleteness due to occlusions and limited sensor viewpoints, making reliable point cloud completion challenging without large supervised datasets. We propose ZVeC, a zero-shot, instance-driven framework that reformulates scene-level completion as compositional object-level reconstruction. By decomposing a scene into semantic object instances, ZVeC reduces reconstruction ambiguity in cluttered environments while eliminating the need for scenario-specific training. Each segmented vehicle is completed independently using a depth- and 3D Gaussian-conditioned diffusion model that exploits generalized geometric priors before the reconstructed instances are recomposed into the original scene. To evaluate our approach, we construct a real-world dense LiDAR benchmark of underground parking environments. Experimental results demonstrate consistent improvements over representative scene-level baselines in both quantitative metrics and visual quality. The completed point cloud differs substantially from the measured input (average KL divergence ~ 2.1), yet reducing the input to only 1% of the original LiDAR measurements changes the completed reconstruction only marginally (KL divergence < 0.50). This demonstrates that ZVeC produces geometrically consistent completions even under extreme input sparsity.
