We show that denoising of 3D point clouds can be learned unsupervised, directly from noisy 3D point cloud data only. This is achieved by extending recent ideas from learning of unsupervised image denoisers to unstructured 3D point clouds. Unsupervised image denoisers operate under the assumption that a noisy pixel observation is a random realization of a distribution around a clean pixel value, which allows appropriate learning on this distribution to eventually converge to the correct value. Regrettably, this assumption is not valid for unstructured points: 3D point clouds are subject to total noise, i. e., deviations in all coordinates, with no reliable pixel grid. Thus, an observation can be the realization of an entire manifold of clean 3D points, which makes a na\"ive extension of unsupervised image denoisers to 3D point clouds impractical. Overcoming this, we introduce a spatial prior term, that steers converges to the unique closest out of the many possible modes on a manifold. Our results demonstrate unsupervised denoising performance similar to that of supervised learning with clean data when given enough training examples - whereby we do not need any pairs of noisy and clean training data.
翻译:我们显示,对 3D 点云的解密可以直接从噪声 3D 点云数据中直接从3D 点云数据中不受监督地学习。 这是通过将最近的想法从学习未受监督的图像隐居器到无结构的 3D 点云的扩展而实现的。 无监督的图像隐居器运行的假设是,噪音像素观测是围绕清洁像素值随机地实现分布的, 这使得关于此分布的适当学习最终能够与正确的值趋同。 遗憾的是, 对于未结构化的点来说,这一假设是无效的: 3D 点云会受到全部噪音的影响, 即所有坐标的偏差, 没有可靠的像素格网。 因此, 观察可以是实现整块干净的 3D 点, 这使得未监督的图像隐居器向 3D 点云不切入。 克服这一假设, 我们引入了空间的前一术语, 将它引向最接近于多种可能模式中的独特最接近点。 我们的结果显示, 与在提供足够高度的训练时, 我们不需要任何清洁数据来的任何操作。