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
this https URL

我们介绍了一种基于自我注意力机制的新型网络，可以软性聚焦于相关点，并通过学习温度参数来调整软性，使其能够在较大的近邻范围内自然而有效地工作。结果，我们的模型比所有现有的正常估计算法表现更好，精度达到 94.1%，比以前的 91.2% 的最高水平快 25 倍小，推理时间快 12 倍。我们还使用点对平面迭代最近点（ICP）作为应用案例，以展示我们的正常估计比其他方法的正常估计更快地收敛，而无需手动微调近邻参数范围。