Good quality reconstruction and comprehension of a scene rely on 3D estimation methods. The 3D information was usually obtained from images by stereo-photogrammetry, but deep learning has recently provided us with excellent results for monocular depth estimation. Building up a sufficiently large and rich training dataset to achieve these results requires onerous processing. In this paper, we address the problem of learning outdoor 3D point cloud from monocular data using a sparse ground-truth dataset. We propose Pix2Point, a deep learning-based approach for monocular 3D point cloud prediction, able to deal with complete and challenging outdoor scenes. Our method relies on a 2D-3D hybrid neural network architecture, and a supervised end-to-end minimisation of an optimal transport divergence between point clouds. We show that, when trained on sparse point clouds, our simple promising approach achieves a better coverage of 3D outdoor scenes than efficient monocular depth methods.

中文翻译：

---

Pix2Point：使用稀疏点云和最佳传输学习户外 3D

场景的高质量重建和理解依赖于 3D 估计方法。3D 信息通常是通过立体摄影测量从图像中获得的，但深度学习最近为我们提供了单眼深度估计的出色结果。建立足够大和丰富的训练数据集来实现这些结果需要繁重的处理。在本文中，我们解决了使用稀疏地面实况数据集从单目数据中学习室外 3D 点云的问题。我们提出了 Pix2Point，这是一种基于深度学习的单目 3D 点云预测方法，能够处理完整且具有挑战性的户外场景。我们的方法依赖于 2D-3D 混合神经网络架构，以及点云之间最佳传输分歧的监督端到端最小化。我们表明，