用概率模型改进NeRF，让激光雷达能准确生成多回波点云。
A Probabilistic Formulation of LiDAR Mapping with Neural Radiance Fields
- 将损失函数改为概率积分，避免虚表面伪影
- 单通道输出可采样首回波、第n回波或最强回波
- 适合需要精确回波分类的自动驾驶场景
本文重新审视神经辐射场（NeRF）在生成场景激光雷达视图时的训练过程。与图像中像素对光进行时间积分不同，激光雷达脉冲在特定时刻到达探测器，因此同一探测器可能产生多个回波，其分类具有内在概率性。采用传统NeRF训练方式可能导致网络在存在冲突测距结果的空旷区域学习到虚假表面，类似于图像模型中的漂浮伪影。我们证明，通过将损失函数定义为概率积分（而非光学密度积分），网络能够为同一射线学习到多个峰值，从而从单一输出通道中采样首回波、第n回波或最强回波。代码已开源：https://github.com/mcdermatt/PLINK。
原文摘要 · Abstract (English)
In this paper we reexamine the process through which a Neural Radiance Field (NeRF) can be trained to produce novel LiDAR views of a scene. Unlike image applications where camera pixels integrate light over time, LiDAR pulses arrive at specific times. As such, multiple LiDAR returns are possible for any given detector and the classification of these returns is inherently probabilistic. Applying a traditional NeRF training routine can result in the network learning phantom surfaces in free space between conflicting range measurements, similar to how floater aberrations may be produced by an image model. We show that by formulating loss as an integral of probability (rather than as an integral of optical density) the network can learn multiple peaks for a given ray, allowing the sampling of first, nth, or strongest returns from a single output channel. Code is available at https://github.com/mcdermatt/PLINK
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。