论文标题
带有表面先验的稀疏点云的重建表面
Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors
论文作者
论文摘要
从3D点云中重建表面是一项重要的任务。当前方法能够通过学习签名距离功能（SDF）从没有地面真相签名距离或点正常的单点云中重建表面。但是，它们要求点云是密集的，这极大地限制了其在实际应用中的性能。为了解决此问题，我们建议用稀疏点云从表面上进行重建高度精确的表面。我们通过将查询投影到稀疏点云表示的表面上来学习SDF。我们的关键想法是通过将查询投影推向表面和投影距离为最小值来推断签名距离。为了实现这一目标，我们在确定一个点是否在稀疏点云上之前训练神经网络以捕获地下表面，然后将其作为可区分的功能利用，以从看不见的稀疏点云中学习SDF。我们的方法可以从单个稀疏点云中学习SDF，而无需地面真相签名或点正常。我们在广泛使用的基准下的数值评估表明，我们的方法达到了最新的重建精度，尤其是对于稀疏点云。
It is an important task to reconstruct surfaces from 3D point clouds. Current methods are able to reconstruct surfaces by learning Signed Distance Functions (SDFs) from single point clouds without ground truth signed distances or point normals. However, they require the point clouds to be dense, which dramatically limits their performance in real applications. To resolve this issue, we propose to reconstruct highly accurate surfaces from sparse point clouds with an on-surface prior. We train a neural network to learn SDFs via projecting queries onto the surface represented by the sparse point cloud. Our key idea is to infer signed distances by pushing both the query projections to be on the surface and the projection distance to be the minimum. To achieve this, we train a neural network to capture the on-surface prior to determine whether a point is on a sparse point cloud or not, and then leverage it as a differentiable function to learn SDFs from unseen sparse point cloud. Our method can learn SDFs from a single sparse point cloud without ground truth signed distances or point normals. Our numerical evaluation under widely used benchmarks demonstrates that our method achieves state-of-the-art reconstruction accuracy, especially for sparse point clouds.
