使用组合神经场的动态 LiDAR 重仿真
Dynamic LiDAR Re-simulation using Compositional Neural Fields
AI总结：
提出 DyNFL 组合神经场方法，通过分离重建静态背景与动态物体并进行光线丢弃组合，实现可编辑、高保真的动态驾驶场景 LiDAR 重仿真。
摘要：
我们提出 DyNFL，这是一种新颖的基于神经场的方法，用于对动态驾驶场景中的 LiDAR 扫描进行高保真重仿真。DyNFL 处理来自动态环境的 LiDAR 测量值，并辅以运动物体的边界框，以构建可编辑的神经场。该场由分别重建的静态背景和动态物体组成，允许用户在重仿真场景中修改视点、调整物体位置并无缝添加或移除物体。我们方法的一项关键创新是神经场组合技术，该技术通过光线丢弃测试有效整合来自各种场景的重建神经资产，并考虑了遮挡和透明表面。我们在合成环境和真实环境中的评估表明，DyNFL 显著改进了动态场景 LiDAR 仿真，兼具物理保真度和灵活的编辑能力。
英文摘要：
We introduce DyNFL, a novel neural field-based approach for high-fidelity re-simulation of LiDAR scans in dynamic driving scenes. DyNFL processes LiDAR measurements from dynamic environments, accompanied by bounding boxes of moving objects, to construct an editable neural field. This field, comprising separately reconstructed static background and dynamic objects, allows users to modify viewpoints, adjust object positions, and seamlessly add or remove objects in the re-simulated scene. A key innovation of our method is the neural field composition technique, which effectively integrates reconstructed neural assets from various scenes through a ray drop test, accounting for occlusions and transparent surfaces. Our evaluation with both synthetic and real-world environments demonstrates that DyNFL substantially improves dynamic scene LiDAR simulation, offering a combination of physical fidelity and flexible editing capabilities.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
