论文标题
邻居不敏感的点云正常估计网络
Neighbourhood-Insensitive Point Cloud Normal Estimation Network
论文作者
论文摘要
我们介绍了一个新型的基于自我注意力的正常估计网络，该网络能够轻柔地专注于相关点并通过学习温度参数来调整柔软度，从而使其能够在较大的邻里范围内自然有效地工作。结果，我们的模型的表现优于所有现有的正常估计算法，相比之下，与先前的ART状态相比，达到94.1％的准确性，型号为91.2％，较小的模型和12倍的推理时间更快。我们还使用点对上的迭代最接近点（ICP）作为应用程序案例，以表明我们的正常估计会比其他方法的正常估计更快，而无需手动微调邻域范围参数。代码可在https://code.active.vision中找到。
We introduce a novel self-attention-based normal estimation network that is able to focus softly on relevant points and adjust the softness by learning a temperature parameter, making it able to work naturally and effectively within a large neighbourhood range. As a result, our model outperforms all existing normal estimation algorithms by a large margin, achieving 94.1% accuracy in comparison with the previous state of the art of 91.2%, with a 25x smaller model and 12x faster inference time. We also use point-to-plane Iterative Closest Point (ICP) as an application case to show that our normal estimations lead to faster convergence than normal estimations from other methods, without manually fine-tuning neighbourhood range parameters. Code available at https://code.active.vision.
